modules_links.md

Modules Links

This file summarizes modules under src/modules, grouped by directory for easier lookup and citation.

Activation

AReLU

• File: Activation/AReLU.py
• Tags: ReLU
• Paper: "AReLU: Attention-based Rectified Linear Unit" (arXiv 2020)
• Code: https://github.com/naturomics/AReLU

BSiLU

• File: Activation/BSiLU.py
• Tags: SiLU
• Paper: "The Resurrection of the ReLU" (arXiv 2025)
• Code:

DynamicTanh

• File: Activation/DynamicTanh.py
• Tags: Tanh
• Paper: "Transformers without Normalization" (CVPR 2025)
• Code: https://github.com/jiachenzhu/DyT

NeLU

• File: Activation/NeLU.py
• Tags: ReLU
• Paper: "The Resurrection of the ReLU" (arXiv 2025)
• Code:

SAFM

• File: Activation/SAFM.py
• Tags: GELU
• Paper: "Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution" (ICCV 2023)
• Code: https://github.com/sunny2109/SAFMN

SMFA

• File: Activation/SMFA.py
• Tags: GELU
• Paper: "SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution" (ECCV 2024)
• Code: https://github.com/Zheng-MJ/SMFANet

TeLU

• File: Activation/TeLU.py
• Tags: Tanh
• Paper: "TeLU Activation Function for Fast and Stable Deep Learning" (arXiv 2025)
• Code: https://github.com/alfredofernandez2021/TeLU-Experiments

Attention

A2Atttention

• File: Attention/A2Atttention.py
• Tags: Spatial, Channel
• Paper: "A^2-Nets: Double Attention Networks" (NIPS 2018)
• Code: https://github.com/cypw/A2-Nets

ACA

• File: Attention/ACA.py
• Tags: Spatial, Channel
• Paper: "Wavelet_and_Adaptive_Coordinate_Attention_Guided_Fine-Grained_Residual_Network_for_Image_Denoising" (TCSVT 2025)
• Code: https://github.com/jjhuangcs/WINNet

ACFM

• File: Attention/ACFM.py
• Tags: Spatial, Channel
• Paper: "CAF-YOLO A Robust Framework for Multi-Scale Lesion Detection in Biomedical Imagery" (ICASSP 2025)
• Code: https://github.com/xiaochen925/CAF-YOLO

ACmix

• File: Attention/ACmix.py
• Tags: Spatial, Channel
• Paper: "On the Integration of Self-Attention and Convolution" (CVPR 2022)
• Code: https://github.com/LeapLabTHU/ACmix

AGCA

• File: Attention/AGCA.py
• Tags: Channel
• Paper: "Attention Guided Context Aggregation Network for Image Dehazing" (IEEE 2023)
• Code: https://github.com/cddlyf/GCANet

ASSA

• File: Attention/ASSA.py
• Tags: Sparse, Linear
• Paper: "Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration" (CVPR 2024)
• Code: https://github.com/joshyZhou/AST

Agent-Attention

• File: Attention/Agent-Attention.py
• Tags: Spatial
• Paper: "Agent Attention: On the Integration of Softmax and Linear Attention" (ECCV 2024)
• Code: https://github.com/LeapLabTHU/Agent-Attention

Area-Attention (AAttn) + ABlock

• File: Attention/Area-Attention.py
• Tags: Spatial
• Paper: "YOLOv12 Attention-Centric Real-Time Object Detectors" (arXiv 2025)
• Code: https://github.com/sunsmarterjie/yolov12

Attention4D

• File: Attention/Attention4D.py
• Tags: Spatial
• Paper: "RDD4D: 4D Attention-Guided Road Damage Detection And Classification" (arXiv 2025)
• Code: https://github.com/msaqib17/Road_Damage_Detection

AttentionGate

• File: Attention/AttentionGate.py
• Tags: Gated
• Paper: "CAD-Unet A Capsule Network-Enhanced Unet Architecture for Accurate Segmentation of COVID-19 Lung Infections from CT Images" (MIA 2025)
• Code: https://github.com/AmanoTooko-jie/CAD-Unet

AxialAttention

• File: Attention/Axial-Attention.py
• Tags: Spatial
• Paper: "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" (MICCAI 2021)
• Code: https://github.com/jeya-maria-jose/Medical-Transformer

BAM

• File: Attention/BAM.py
• Tags: Spatial, Channel
• Paper: "BAM: Bottleneck Attention Module" (BMVC 2018)
• Code: https://github.com/Jongchan/attention-module

Bi-Level Routing Attention

• File: Attention/Bi-LevelRoutingAttention.py
• Tags: Sparse
• Paper: "Bi-Former: Vision Transformer with Bi-Level Routing Attention" (CVPR 2023)
• Code: https://github.com/rayleizhu/BiFormer

CAA

• File: Attention/CAA.py
• Tags: Spatial, Channel
• Paper: "Poly Kernel Inception Network for Remote Sensing Detection" (CVPR 2024)
• Code: https://github.com/NUST-Machine-Intelligence-Laboratory/PKINet

CAFM

• File: Attention/CAFM.py
• Tags: Linear
• Paper: "Content-Aware Feature Modulation for Single Image Super-Resolution" (IEEE 2023)
• Code: https://github.com/JingyunLiang/SwinIR

CAFM

• File: Attention/CAFM_Fusion.py
• Tags: Linear
• Paper: "Content-Aware Feature Modulation for Single Image Super-Resolution" (IEEE 2023)
• Code: https://github.com/JingyunLiang/SwinIR

CAFM

• File: Attention/CAFM_Spatial.py
• Tags: Spatial
• Paper: "Hybrid Convolutional and Attention Network for Hyperspectral Image Denoising" (GRSL 2024)
• Code: https://github.com/summitgao/HCANet

CAN

• File: Attention/CAN.py
• Tags: Spatial
• Paper: "Contextual Attention Network for Semantic Segmentation in Remote Sensing Imagery" (ICPR 2021)
• Code: https://github.com/Ruiyang-Zhang/Contextual_Attention_Network

CASAtt

• File: Attention/CASAtt.py
• Tags: Spatial, Channel
• Paper: "CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications" (arXiv 2025)
• Code: https://github.com/Tianfang-Zhang/CAS-ViT

CA Block

• File: Attention/CA_Block.py
• Tags: Channel, Gated
• Paper: "MogaNet: Multi-order Gated Aggregation Network" (ICLR 2024)
• Code: https://github.com/Westlake-AI/MogaNet

CBAM

• File: Attention/CBAM.py
• Tags: Spatial, Channel
• Paper: "CBAM: Convolutional Block Attention Module" (ECCV 2018)
• Code: https://github.com/Jongchan/attention-module

CEB

• File: Attention/CEB.py
• Tags: Channel, Gated
• Paper: "Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion" (TIP 2025)
• Code: https://github.com/SunHui1216/SFMFusion

CFBlock

• File: Attention/CFBlock.py
• Tags: Spatial
• Paper: "SCTNet: Single-Branch CNN with Transformer-like Multi-scale Context Aggregation" (AAAI 2024)
• Code: https://github.com/xzz777/SCTNet

CMA

• File: Attention/CMA.py
• Tags: Cross
• Paper: "SalM^2 An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention" (AAAI 2025)
• Code: https://github.com/zhao-chunyu/SaliencyMamba

CPAM

• File: Attention/CPAM.py
• Tags: Channel, Spatial
• Paper: "ASF-YOLO: A Novel YOLO Model with Attentional Scale Sequence Fusion for Cell Instance Segmentation" (IMAVIS 2024)
• Code: https://github.com/mkang315/ASF-YOLO

CPCA

• File: Attention/CPCA.py
• Tags: Channel
• Paper: "CPCANet: Channel Prior Convolutional Attention for Medical Image Segmentation" (Elsevier 2024)
• Code: https://github.com/Cuthbert-Huang/CPCANet

CRA

• File: Attention/CRA.py
• Tags: Channel
• Paper: "MetaSeg: MetaFormer-Based Global Contexts-Aware Network for Efficient Semantic Segmentation" (WACV 2024)
• Code: https://github.com/hyunwoo137/MetaSeg

CSAM

• File: Attention/CSAM.py
• Tags: Spatial, Channel
• Paper: "Striking a better balance between segmentation performance and computational costs with a minimalistic network design" (ASOC 2025)
• Code: https://github.com/duweidai/BMIS

CSA_ConvBlock

• File: Attention/CSA_ConvBlock.py
• Tags: Channel
• Paper: "Flat U-Net An Efficient Ultralightweight Model for Solar Filament Segmentation inFull-disk Hα Images" (arXiv 2025)
• Code: https://github.com/fly2100/Flat-UNet

Channel Attention

• File: Attention/Channel_Attention.py
• Tags: Channel
• Paper: "Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution" (AAAI 2025)
• Code: https://github.com/saturnian77/ASID/tree/master

CoTAttention

• File: Attention/CoTAttention.py
• Tags: Spatial
• Paper: "Contextual Transformer Networks for Visual Recognition" (CVPR 2021)
• Code: https://github.com/JDAI-CV/CoTNet

Compact Self Attention

• File: Attention/Compact_Self_Attention.py
• Tags: Spatial
• Paper: "GridFormer Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions" (2025)
• Code: https://github.com/TaoWangzj/GridFormer

ConvAttn

• File: Attention/ConvAttn.py
• Tags: Spatial
• Paper: "Emulating Self-attention with Convolution for Efficient Image Super-Resolution" (ICCV 2025)
• Code: https://github.com/dslisleedh/ESC

ConvSAtt

• File: Attention/ConvSAtt.py
• Tags: Spatial
• Paper: "Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition" (TPAMI 2024)
• Code: https://github.com/HVision-NKU/Conv2Former

CoordAttention

• File: Attention/CoordAttention.py
• Tags: Spatial, Channel
• Paper: "Coordinate Attention for Efficient Mobile Network Design" (CVPR 2021)
• Code: https://github.com/houqb/CoordAttention

CoordGate

• File: Attention/CoordGate.py
• Tags: Gated
• Paper: "CoordGate: Efficiently Computing Spatially-Varying Convolutions in CNNs" (arXiv 2024)
• Code: https://github.com/damo-cv/CoordGate

Criss Cross Attention

• File: Attention/Criss_Cross_Attention.py
• Tags: Spatial
• Paper: "CCNet: Criss-Cross Attention for Semantic Segmentation" (TPAMI 2020 & ICCV 2019)
• Code: https://github.com/speedinghzl/CCNet

Cross-Shaped-Window-Self-Attention

• File: Attention/Cross-Shaped-Window-Self-Attention.py
• Tags: Spatial
• Paper: "CSWin-UNet Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation" (INFFUS 2025)
• Code: https://github.com/eatbeanss/CSWin-UNet

CSAM

• File: Attention/Cross-Slice_Attention.py
• Tags: Spatial, Channel
• Paper: "CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image Segmentation" (WACV 2024)
• Code: https://github.com/aL3x-O-o-Hung/CSAM

DANet

• File: Attention/DANet.py
• Tags: Spatial, Channel
• Paper: "Dual Attention Network for Scene Segmentation" (CVPR 2019)
• Code: https://github.com/junfu1115/DANet

DAT

• File: Attention/DAT.py
• Tags: Deformable
• Paper: "Vision Transformer with Deformable Attention" (CVPR 2022)
• Code: https://github.com/LeapLabTHU/DAT

DCAFE

• File: Attention/DCAFE.py
• Tags: Spatial, Channel
• Paper: "Flora-NET Integrating dual coordinate attention with adaptive kernel based convolution network for medicinal flower identification" (Elsevier 2025)
• Code: https://github.com/ersachingupta11/Flora-NET

DLKA

• File: Attention/DLKA.py
• Tags: Deformable, Large-Kernel
• Paper: "Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation" (WACV 2024)
• Code: https://github.com/xmindflow/DLKA

DSAM

• File: Attention/DSAM.py
• Tags: Spatial
• Paper: "Boundary-Aware_Feature_Fusion_With_Dual-Stream_Attention_for_Remote_Sensing_Small_Object_Detection" (TGRS 2025)
• Code: https://github.com/ooo1128/BAFNet

DSPM

• File: Attention/DSPM.py
• Tags: Spatial, Channel
• Paper: "HAFNet_Hierarchical_Attention_Fusion_Network_for_Infrared_Small_Target_Detection" (TGRS 2025)
• Code: https://github.com/Wangtao-Bao/HAFNet

DSSA

• File: Attention/DSSA.py
• Tags: Sparse, Linear
• Paper: "DSSAU-NetU-Shaped Hybrid Network for Pubic Symphysis and Fetal Head Segmentation" (arXiv 2025)
• Code: https://github.com/XiaZunhui/DSSAU-Net

Deformable Interactive Attention

• File: Attention/Deformable_Interactive_Attention.py
• Tags: Deformable
• Paper: "An Adaptive Dual-Supervised Cross-Deep Dependency Network for Pixel-Wise Classification" (TGRS 2025)
• Code: https://github.com/ChenC1027/ADCD-Net/tree/main

Deformable Self Attention

• File: Attention/Deformable_Self_Attention.py
• Tags: Deformable
• Paper: "Content-Aware Transformer for All-in-one Image Restoration" (arXiv 2025)
• Code: https://github.com/Aitical/DSwinIR

Deformable Spatial Attention (DSA)

• File: Attention/Deformable_Spatial_Attention.py
• Tags: Deformable
• Paper: "DSAN Exploring the Relationship between Deformable Convolution and Spatial Attention" (TNNLS 2025)
• Code: https://github.com/MarcYugo/DSAN-Deformable-Spatial-Attention

DiffAttention

• File: Attention/DiffAttention.py
• Tags: Linear
• Paper: "DiffCLIP Differential Attention Meets CLIP" (arXiv 2025)
• Code: https://github.com/hammoudhasan/DiffCLIP

Dynamic-CBAM

• File: Attention/Dynamic-CBAM.py
• Tags: Dynamic
• Paper: "Emotional Vietnamese Speech-Based Depression Diagnosis Using Dynamic Attention Mechanism" (ICAMCS 2024)
• Code: https://github.com/fiyud/Emotional-Vietnamese-Speech-Based-Depression-Diagnosis-Using-Dynamic-Attention-Mechanism

Dynamic-range Histogram Self-Attention

• File: Attention/Dynamic-range_Histogram_Self-Attention.py
• Tags: Dynamic
• Paper: "Histoformer: Dynamic-range Histogram Self-Attention for Depth Estimation" (ECCV 2024)
• Code: https://github.com/sunshangquan/Histoformer

DynamicSpatialAttention

• File: Attention/DynamicSpatialAttention.py
• Tags: Spatial
• Paper: "DRPCA-Net Make Robust PCA Great Again for Infrared Small Target Detection" (TGRS 2025)
• Code: https://github.com/GrokCV/DRPCA-Net

ECA

• File: Attention/ECA.py
• Tags: Channel
• Paper: "ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks (CVPR 2020)" (arXiv 2019)
• Code: https://github.com/BangguWu/ECANet

ELA

• File: Attention/ELA.py
• Tags: Spatial
• Paper: "ELA: Efficient Local Attention for Deep Convolutional Neural Networks" (arXiv 2024)
• Code: https://github.com/xmu-xiaoma666/ELA

ELGCA

• File: Attention/ELGCA.py
• Tags: Channel
• Paper: "ELGCNet: Efficient Local-Global Context Network for Remote Sensing Image Super-Resolution" (TGRS 2024)
• Code: https://github.com/techmn/elgcnet

EMA

• File: Attention/EMA.py
• Tags: Channel
• Paper: "Efficient Multi-Scale Attention Module with Cross-Spatial Learning" (ICASSP 2023)
• Code: https://github.com/xmu-xiaoma666/External-Attention-pytorch

EMSA

• File: Attention/EMSA.py
• Tags: Spatial
• Paper: "ResT: An Efficient Transformer with Thread-Interaction" (NeurIPS 2021)
• Code: https://github.com/wofmanaf/ResT

ESSAttn

• File: Attention/ESSAttn.py
• Tags: Spatial
• Paper: "ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution" (ICCV 2023)
• Code: https://github.com/Rexzhan/ESSAformer

EfficientAdditiveAttnetion

• File: Attention/EfficientAdditiveAttnetion.py
• Tags: Spatial
• Paper: "SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications" (ICCV 2023)
• Code: https://github.com/Amshaker/SwiftFormer

EfficientAttention

• File: Attention/EfficientAttention.py
• Tags: Spatial
• Paper: "Efficient Attention: Attention with Linear Complexities" (arXiv 2024)
• Code: https://github.com/cmsflash/efficient-attention

External Attention

• File: Attention/ExternalAttention.py
• Tags: Spatial
• Paper: "Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks" (arXiv 2021)
• Code: https://github.com/xmu-xiaoma666/External-Attention-pytorch

FU-SE

• File: Attention/FU-SE.py
• Tags: Channel
• Paper: "MobileIE An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices" (ICCV 2025)
• Code: https://github.com/AVC2-UESTC/MobileIE

FCM (Feature_Complementary_Mapping)

• File: Attention/Feature_Complementary_Mapping.py
• Tags: Channel, Spatial
• Paper: "FBRT-YOLO Faster and Better for Real-Time Aerial Image Detection" (AAAI 2025)
• Code: https://github.com/galaxy-oss/FCM

FCM (Feature_Correction_Module)

• File: Attention/Feature_Correction_Module.py
• Tags: Channel
• Paper: "CFFormer_A_Cross-Fusion_Transformer_Framework_for_the_Semantic_Segmentation_of_Multisource_Remote_Sensing_Images" (TGRS 2025)
• Code: https://github.com/masurq/CFFormer

Fine-grained Channel Attention

• File: Attention/Fine-grained_Channel_Attention.py
• Tags: Channel
• Paper: "Unsupervised Bidirectional Contrastive Reconstruction and Adaptive Fine-Grained Channel Attention Networks" (NN 2024)
• Code: https://github.com/Lose-Code/UBRFC-Net

FrequencyAttention

• File: Attention/FrequencyAttention.py
• Tags: Frequency
• Paper: "FMNet Frequency-Assisted Mamba-Like Linear Attention Network for Camouflaged Object Detection" (arXiv 2025)
• Code: https://github.com/Chranos/FMNet

FrequencySemanticAttention

• File: Attention/FrequencySemanticAttention.py
• Tags: Channel
• Paper: "MobileIE An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices" (ICCV 2025)
• Code: https://github.com/AVC2-UESTC/MobileIE

FrequencySemanticAttention2D

• File: Attention/FrequencySemanticAttention2D.py
• Tags: Channel
• Paper: "MobileIE An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices" (ICCV 2025)
• Code: https://github.com/AVC2-UESTC/MobileIE

Frequency Strip Attention

• File: Attention/Frequency_Strip_Attention.py
• Tags: Spatial
• Paper: "DSANet: Dual-stream attention network for cerebrovascular segmentation in TOF-MRA" (NN 2024)
• Code: https://github.com/c-yn/DSANet

FullyAttentional

• File: Attention/FullyAttentional.py
• Tags: Spatial
• Paper: "MetaFormer Is Actually What You Need for Vision" (CVPR 2022)
• Code: https://github.com/sail-sg/poolformer

GA

• File: Attention/GA.py
• Tags: Global
• Paper: "Learned Focused Plenoptic Image Compression with Microimage Preprocessing and Global Attention" (2025)
• Code: https://github.com/VincentChandelier/GACN

GAG

• File: Attention/GAG.py
• Tags: Gated
• Paper: "MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation" (ICCV 2025)
• Code: https://github.com/SLDGroup/MK-UNet

GCSA

• File: Attention/GCSA.py
• Tags: Spatial
• Paper: "Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising" (AAAI 2025)
• Code: https://github.com/nagejacob/TBSN

GLCA

• File: Attention/GLCA.py
• Tags: Channel
• Paper: "SC-MambaFew Few-shot learning based on Mamba and selective spatial-channel attention for bearing fault diagnosis" (Elsevier 2025)
• Code: https://github.com/giabao804/few-shot-mamba

GRSA

• File: Attention/GRSA.py
• Tags: Spatial
• Paper: "" (ACM MM 2024)
• Code:

GeometrySelf-Attention

• File: Attention/GeometrySelf-Attention.py
• Tags: Spatial
• Paper: "DFormerv2 Geometry Self-Attention for RGBD Semantic Segmentation" (CVPR 2025)
• Code: https://github.com/VCIP-RGBD/DFormer

GroupCBAMEnhancer

• File: Attention/GroupCBAMEnhancer.py
• Tags: Spatial, Channel
• Paper: "Multiscale_Sparse_Cross-Attention_Network_for_Remote_Sensing_Scene_Classification" (TGRS 2025)
• Code: https://github.com/TangXu-Group/Remote-Sensing-Images-Classification/tree/main/MSCN

HRAMi

• File: Attention/HRAMi.py
• Tags: Spatial
• Paper: "RAMiT: Relational Attention via Multi-scale Inter-Token Relations for Vision Transformers" (CVPR 2024)
• Code: https://github.com/rami0205/RAMiT

HSPA

• File: Attention/HSPA.py
• Tags: Spatial
• Paper: "Hybrid Scale-Aware and Prior-Guided Attention Network for Image Dehazing" (TIP 2024)
• Code: https://github.com/laoyangui/HSPAN

HaloAttention

• File: Attention/HaloAttention.py
• Tags: Spatial
• Paper: "Scaling Local Self-Attention for Parameter Efficient Visual Backbones" (ICCV 2021)
• Code: https://github.com/kakaobrain/halo

HiLo

• File: Attention/HiLo.py
• Tags: Spatial
• Paper: "HiLo: A High-Low Frequency Attention Network for Unmatched Metric Learning" (NeurIPS 2022)
• Code: https://github.com/ShapovalovR/HiLo

Hybrid pooling attention (HPA)

• File: Attention/Hybrid_Pooling_Attention.py
• Tags: Spatial
• Paper: "A synergistic CNN-transformer network with pooling attention fusion for hyperspectral image classification" (DSP 2025)
• Code: https://github.com/chenpeng052/synergisticNet

IIA

• File: Attention/IIA.py
• Tags: Channel
• Paper: "A Lightweight Semantic Segmentation Network Based on Self-Attention Mechanism and State Space Model for Efficient Urban Scene Segmentation" (TGRS 2025)
• Code: https://github.com/takeyoutime/UMFormer

InterSliceSelfAttention

• File: Attention/InterSliceSelfAttention.py
• Tags: Temporal
• Paper: "HCMA-UNet A Hybrid CNN-Mamba UNet with Inter-Slice Self-Attention for Efficient Breast Cancer Segmentation" (arXiv 2025)
• Code: https://github.com/Haoxuanli-Thu/HCMA-UNet

KEPSVGP

• File: Attention/KEPSVGP.py
• Tags: Sparse
• Paper: "Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes" (ICML 2024)
• Code:

LEGM

• File: Attention/LEGM.py
• Tags: Spatial
• Paper: "ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation" (CVPR 2024)
• Code: https://github.com/NargesNorouzi/ALGM

LIA

• File: Attention/LIA.py
• Tags: Spatial
• Paper: "PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution" (ACCV 2024)
• Code: https://github.com/icandle/PlainUSR

LSA

• File: Attention/LSA.py
• Tags: Spatial
• Paper: "Unsupervised Spectral Demosaicing with Lightweight Spectral Attention Networks" (TIP 2025)
• Code: https://github.com/fkmajiji/Unsupervised-Spectral-Demosaicing

LSGAttention

• File: Attention/LSGAttention.py
• Tags: Gated
• Paper: "Long Short-Range Gated Attention for Image Dehazing" (TIM 2023)
• Code: https://github.com/BookerDeWitt/LSG-Attention

LSK

• File: Attention/LSK.py
• Tags: Spatial
• Paper: "Large Selective Kernel Network for Remote Sensing Object Detection" (IJCV 2024)
• Code: https://github.com/zcablii/Large-Selective-Kernel-Network

LWGA

• File: Attention/LWGA.py
• Tags: Spatial
• Paper: "LWGANet A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks" (arXiv 2025)
• Code: https://github.com/lwCVer/LWGANet

Lightweight Cross Attention

• File: Attention/Lightweight_Cross_Attention.py
• Tags: Cross
• Paper: "HVI A New Color Space for Low-light Image Enhancement" (CVPR 2025)
• Code: https://github.com/Fediory/HVI-CIDNet

LiteMLA

• File: Attention/LiteMLA.py
• Tags: Spatial
• Paper: "EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction" (ICCV 2023)
• Code: https://github.com/mit-han-lab/efficientvit

LRSA

• File: Attention/Local_Region_Self-Attention.py
• Tags: Spatial
• Paper: "ATANet Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution" (CVPR 2025)
• Code: https://github.com/EquationWalker/CATANet/tree/main

LRSA

• File: Attention/Low-Resolution_Self-Attention.py
• Tags: Spatial
• Paper: "Low-Resolution Self-Attention for Semantic Segmentation" (TPAMI 2025)
• Code: https://github.com/yuhuan-wu/LRFormer

MALA

• File: Attention/MALA.py
• Tags: Spatial
• Paper: "Rectifying Magnitude Neglect in Linear Attention" (ICCV 2025)
• Code: https://github.com/qhfan/MALA

MCAM

• File: Attention/MCAM.py
• Tags: Channel
• Paper: "MCANet: Medical Image Segmentation with Multi-Scale Cross-Attention Mechanism (Computers in Biology and Medicine)" (Elsevier 2022)
• Code: https://github.com/Ray010221/MCANet

MFM

• File: Attention/MFM.py
• Tags: Spatial
• Paper: "Memory-Scalable and Simplified Functional Map Learning" (CVPR 2024)
• Code: https://github.com/RobinMagnet/SimplifiedFunctionalMaps

MHRSA

• File: Attention/MHRSA.py
• Tags: Spatial
• Paper: "Mixed Attention Network for Hyperspectral Image Denoising" (arXiv 2023)
• Code: https://github.com/ZhaozhiW/MAN_HSI_Denoising

MLCA

• File: Attention/MLCA.py
• Tags: Channel
• Paper: "MLCA: A Mixed Local Channel Attention architecture for deep learning models (Engineering Applications of Artificial Intelligence 2023)" (2023)
• Code: https://github.com/wandahangFY/MLCA

MLLA

• File: Attention/MLLA.py
• Tags: Linear
• Paper: "Demystify Mamba in Vision: A Linear Attention Perspective" (NeurIPS 2024)
• Code: https://github.com/LeapLabTHU/MLLA

MSAM

• File: Attention/MSAM.py
• Tags: Spatial
• Paper: "A Lightweight Semantic Segmentation Network Based on Self-Attention Mechanism and State Space Model for Efficient Urban Scene Segmentation" (TGRS 2025)
• Code: https://github.com/takeyoutime/UMFormer

MSC

• File: Attention/MSC.py
• Tags: Sparse
• Paper: "Multiscale Sparse Cross-Attention Network for Remote Sensing Scene Classification" (TGRS 2025)
• Code: https://github.com/TangXu-Group/Remote-Sensing-Images-Classification/tree/main/MSCN

MSLA

• File: Attention/MSLA.py
• Tags: Linear
• Paper: "MSLAU-Net A Hybird CNN-Transformer Network for Medical Image Segmentation" (arXiv 2025)
• Code: https://github.com/Monsoon49/MSLAU-Net

MUSEAttention

• File: Attention/MUSEAttention.py
• Tags: Spatial
• Paper: "MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning" (arXiv 2019)
• Code: https://github.com/xmu-xiaoma666/External-Attention-pytorch

MWSAttention

• File: Attention/MWSAttention.py
• Tags: Spatial
• Paper: "Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising" (AAAI 2025)
• Code: https://github.com/nagejacob/TBSN

MaskAttention

• File: Attention/MaskAttention.py
• Tags: Sparse
• Paper: "MaskAttn-UNet A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation" (ICCV 2025)
• Code: https://github.com/Belis0811/MaskUnet

MaskedSeparableAttention

• File: Attention/MaskedSeparableAttention.py
• Tags: Spatial
• Paper: "CamoFormer: Masked Separable Attention for Camouflaged Object Detection" (TPAMI 2024)
• Code: https://github.com/BowenQu/CamoFormer

MoHAttention

• File: Attention/MoHAttention.py
• Tags: Spatial
• Paper: "MoH: Multi-Head Attention as Mixture-of-Head Attention" (arXiv 2024)
• Code: https://github.com/SkyworkAI/MoH

Mult-Collaborative-Attention

• File: Attention/Mult-Collaborative-Attention.py
• Tags: Gated
• Paper: "Mult-Collaborative-Attention (Engineering Applications of Artificial Intelligence)" (Elsevier 2023)
• Code: https://github.com/ndsclark/MCANet

MultiDilatelocalAttention

• File: Attention/MultiDilatelocalAttention.py
• Tags: Spatial
• Paper: "DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition" (TMM 2023)
• Code: https://github.com/Jiawei-Yang/DilateFormer

NAM

• File: Attention/NAM.py
• Tags: Channel
• Paper: "NAM: Normalization-based Attention Module" (NeurIPS 2021)
• Code: https://github.com/Christian-lyc/NAM

OrthoNets

• File: Attention/OrthoNets.py
• Tags: Channel
• Paper: "OrthoNets: Orthogonal Channel Attention Networks" (IEEE BigData 2023)
• Code: https://github.com/hady1011/OrthoNets

OutlookAttention

• File: Attention/OutlookAttention.py
• Tags: Spatial
• Paper: "VOLO: Vision Outlooker for Visual Recognition" (TPAMI 2021)
• Code: https://github.com/sail-sg/volo

PGSSA

• File: Attention/PGSSA.py
• Tags: Spatial
• Paper: "MP-HSIR A Multi-Prompt Framework for Universal Hyperspectral ImageRestoration" (arXiv 2025)
• Code: https://github.com/ZhehuiWu/MP-HSIR

PKIBlock

• File: Attention/PKIBlock.py
• Tags: Channel
• Paper: "Poly Kernel Inception Network for Remote Sensing Detection" (CVPR 2024)
• Code: https://github.com/NUST-Machine-Intelligence-Laboratory/PKINet

PSA

• File: Attention/PSA.py
• Tags: Spatial
• Paper: "EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network" (arXiv 2022)
• Code: https://github.com/murufeng/EPSANet

ParNetAttention

• File: Attention/ParNetAttention.py
• Tags: Channel
• Paper: "Non-Deep Networks" (NeurIPS 2022)
• Code: https://github.com/google-research/google-research/tree/master/parnet

ParallelPolarizedSelfAttention

• File: Attention/ParallelPolarizedSelfAttention.py
• Tags: Spatial
• Paper: "Polarized Self-Attention: Towards High-quality Pixel-wise Regression" (arXiv 2021)
• Code: https://github.com/DeLightCMU/PSA

PnPNystraAttention

• File: Attention/PnPNystraAttention.py
• Tags: Linear
• Paper: "Plug-and-Play Linear Attention for Pre-trained Image and Video Restoration Models" (IEEE 2025)
• Code: https://github.com/Srinivas-512/PnP_Nystra

PolaLinearAtt

• File: Attention/PolaLinearAtt.py
• Tags: Linear
• Paper: "PolarFormer Polarity-aware Linear Attention for Vision Transformers" (ICLR 2025)
• Code: https://github.com/ZacharyMeng/PolaFormer

PolarizedSelfAttention

• File: Attention/PolarizedSelfAttention.py
• Tags: Spatial
• Paper: "Polarized Self-Attention: Towards High-quality Pixel-wise Regression" (arXiv 2021)
• Code: https://github.com/DeLightCMU/PSA

QuadrangleAttention

• File: Attention/QuadrangleAttention.py
• Tags: Spatial
• Paper: "Vision Transformer With Quadrangle Attention" (TPAMI 2023)
• Code: https://github.com/ViTAE-Transformer/QFormer

RCSSC

• File: Attention/RCSSC.py
• Tags: Spatial, Channel
• Paper: "ASCNet_Asymmetric_Sampling_Correction_Network_for_Infrared_Image_Destriping" (TGRS 2025)
• Code: https://github.com/xdFai/ASCNet/tree/main

RG_SA

• File: Attention/RG_SA.py
• Tags: Gated
• Paper: "RGT: Recursive Gated Transformer" (ICLR 2024)
• Code: https://github.com/zhengchen1999/RGT

RegionalAttention

• File: Attention/RegionalAttention.py
• Tags: Spatial
• Paper: "Regional Attention for Shadow Removal" (ACM MM 2024)
• Code: https://github.com/CalcuLuUus/RASM

Relation-Aware_Global_Attention

• File: Attention/Relation-Aware_Global_Attention.py
• Tags: Global
• Paper: "Relation-Aware Global Attention for Person Re-identification" (CVPR 2020)
• Code: https://github.com/microsoft/Relation-Aware-Global-Attention-Networks

RelationAwareAttention

• File: Attention/RelationAwareAttention.py
• Tags: Spatial
• Paper: "LP-DETR Layer-wise Progressive Relations for Object Detection" (arXiv 2025)
• Code: https://github.com/authors776/LP-DETR

ResidualAttention

• File: Attention/ResidualAttention.py
• Tags: Spatial
• Paper: "Residual Attention: A Simple but Effective Method for Multi-Label Recognition" (ICCV 2021)
• Code: https://github.com/VegeWong/ResAtt

S2Attention

• File: Attention/S2Attention.py
• Tags: Spatial
• Paper: "S^2-MLPv2: Improved Spatial-Shift MLP Architecture for Vision" (arXiv 2021)
• Code: https://github.com/yu-tanaka/S2-MLP

SCA_ConvBlock

• File: Attention/SCA_ConvBlock.py
• Tags: Channel
• Paper: "Flat U-Net An Efficient Ultralightweight Model for Solar Filament Segmentation inFull-disk Hα Images" (arXiv 2025)
• Code: https://github.com/fly2100/Flat-UNet

SCSA (Spatial and Channel Synergistic Attention)

• File: Attention/SCSA.py
• Tags: Sparse
• Paper: "SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention" (arXiv 2024)
• Code: https://github.com/HZAI-ZJNU/SCSA

SE

• File: Attention/SE.py
• Tags: Channel
• Paper: "Squeeze-and-Excitation Networks" (CVPR 2018)
• Code: https://github.com/hujie-frank/SENet

SGE

• File: Attention/SGE.py
• Tags: Channel
• Paper: "Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks" (arXiv 2019)
• Code: https://github.com/implus/PytorchInsight

SKAttention

• File: Attention/SKAttention.py
• Tags: Channel
• Paper: "Selective Kernel Networks" (CVPR 2019)
• Code: https://github.com/implus/SKNet

SPCSA

• File: Attention/SPCSA.py
• Tags: Gated
• Paper: "Cross Paradigm Representation and Alignment Transformer for Image Deraining" (ACM MM 2025)
• Code: https://github.com/zs1314/CPRAformer

ScaledDotProductAttention

• File: Attention/ScaledDotProductAttention.py
• Tags: Spatial
• Paper: "Attention Is All You Need" (NeurIPS 2017)
• Code: https://github.com/jadore801120/attention-is-all-you-need-pytorch

Sea_Attention

• File: Attention/Sea_Attention.py
• Tags: Spatial
• Paper: "SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic Segmentation" (ICLR 2023)
• Code: https://github.com/fudan-zvg/SeaFormer

SCSA (Semantic Continuous-Sparse Attention)

• File: Attention/Semantic_Continuous-Sparse_Attention.py
• Tags: Sparse
• Paper: "SCSA A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer" (CVPR 2025)
• Code: https://github.com/scn-00/SCSA

ShuffleAttention

• File: Attention/ShuffleAttention.py
• Tags: Channel
• Paper: "SA-Net: Shuffle Attention for Deep Convolutional Neural Networks" (ICASSP 2021)
• Code: https://github.com/wofmanaf/SA-Net

SimAM

• File: Attention/SimAM.py
• Tags: Spatial
• Paper: "SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks" (ICML 2021)
• Code: https://github.com/ZjjConan/SimAM

SimplifiedSelfAttention

• File: Attention/SimplifiedSelfAttention.py
• Tags: Spatial
• Paper: "Simplified Self-Attention for Transformer-based End-to-End Speech Recognition" (arXiv 2020)
• Code:

Single-Head Self-Attention

• File: Attention/Single-Head_Self-Attention.py
• Tags: Spatial
• Paper: "SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design" (CVPR 2024)
• Code: https://github.com/ysj9909/SHViT

Sparse_Self_Attention

• File: Attention/Sparse_Self_Attention.py
• Tags: Sparse
• Paper: "SparseViT Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer" (AAAI 2025)
• Code: https://github.com/scu-zjz/SparseViT

Spatial-Temporal Attention (STAtten)

• File: Attention/Spatial-Temporal_Attention.py
• Tags: Temporal
• Paper: "Spiking Transformer with Spatial-Temporal Attention" (CVPR 2025)
• Code: https://github.com/Intelligent-Computing-Lab-Yale/STAtten

Spatial Attention Module (SAM)

• File: Attention/Spatial_Attention_Module.py
• Tags: Spatial
• Paper: "Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution" (AAAI 2025)
• Code: https://github.com/saturnian77/ASID/tree/master

Spatial Strip Attention

• File: Attention/Spatial_Strip_Attention.py
• Tags: Spatial
• Paper: "DSANet: Dual-stream attention network for cerebrovascular segmentation in TOF-MRA" (NN 2024)
• Code: https://github.com/c-yn/DSANet

Temporal Attention

• File: Attention/Temporal_Attention.py
• Tags: Temporal
• Paper: "FSTA-SNNFrequency-Based Spatial-Temporal Attention Module for SpikingNeural Networks" (AAAI 2025)
• Code: https://github.com/yukairong/FSTA-SNN

TiedSE

• File: Attention/TiedSE.py
• Tags: Channel
• Paper: "Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters" (AAAI 2021)
• Code: https://github.com/TiedBlockConv/TiedBlockConv

Token_Selective_Attention

• File: Attention/Token_Selective_Attention.py
• Tags: Spatial
• Paper: "Dual selective fusion transformer network for hyperspectral image classification" (NN 2025)
• Code: https://github.com/YichuXu/DSFormer

Token Statistics Self-Attention (TSSA)

• File: Attention/Token_Statistics_Self-Attention.py
• Tags: Spatial
• Paper: "Token Statistics Transformer Linear-Time Attention via Variational Rate Reduction" (ICLR 2025)
• Code: https://github.com/RobinWu218/ToST

Top_K_Sparse_Attention

• File: Attention/Top_K_Sparse_Attention.py
• Tags: Sparse
• Paper: "Learning a Sparse Transformer Network for Effective Image Deraining" (CVPR 2023)
• Code: https://github.com/cschen-1217/DRSformer

TripletAttention

• File: Attention/TripletAttention.py
• Tags: Spatial, Channel
• Paper: "Rotate to Attend: Convolutional Triplet Attention Module" (WACV 2021)
• Code: https://github.com/landskape-ai/triplet-attention

UFOAttention

• File: Attention/UFOAttention.py
• Tags: Spatial
• Paper: "UFO-ViT: High Performance Linear Vision Transformer without Softmax" (arXiv 2021)
• Code: https://github.com/UFO-ViT/UFO-ViT

VolSA

• File: Attention/VolSA.py
• Tags: Spatial
• Paper: "VolFormer Explore More Comprehensive Cube Interaction for Hyperspectral Image Restoration and Beyond" (CVPR 2025)
• Code: https://github.com/yudadabing/VolFormer

Convolution

Adaptive Rectangular Convolution (ARConv)

• File: Convolution/Adaptive_Rectangular_Conv.py
• Tags: Large-Kernel
• Paper: "Adaptive Rectangular Convolution for Remote Sensing Pansharpening" (CVPR 2025)
• Code: https://github.com/WangXueyang-uestc/ARConv

AttentionGhostModule

• File: Convolution/AttentionGhostModule.py
• Tags: Lightweight, Depthwise
• Paper: "Attention GhostUNet++ Enhanced Segmentation of Adipose Tissue and Liver in CT Images" (arXiv 2025)
• Code: https://github.com/MansoorHayat777/Attention-GhostUNetPlusPlus

CG-Half-Conv

• File: Convolution/CG-Half-Conv.py
• Tags: Lightweight
• Paper: "Channel grouping vision transformer for lightweight fruit and vegetable recognition" (ESWA 2025)
• Code: https://github.com/Axboexx/CGViT

CondConv

• File: Convolution/CondConv.py
• Tags: Dynamic
• Paper: "CondConv: Conditionally Parameterized Convolutions for Efficient Inference" (NeurIPS 2019)
• Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/condconv

ContMix

• File: Convolution/ContMix.py
• Tags: Large-Kernel
• Paper: "OverLoCK An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels" (CVPR 2025)
• Code: https://github.com/LMMMEng/OverLoCK/tree/main

CosinConv

• File: Convolution/CosinConv.py
• Tags: Dynamic
• Paper: "A Tree-guided CNN for image super-resolution" (arXiv 2025)
• Code: https://github.com/hellloxiaotian/TSRNet

DCNv2

• File: Convolution/DCNv2.py
• Tags: Deformable
• Paper: "Deformable ConvNets v2: More Deformable, Better Results" (CVPR 2019)
• Code: https://github.com/CharlesShang/DCNv2

DSConv

• File: Convolution/DSConv.py
• Tags: Dynamic
• Paper: "Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation (ICCV 2023)" (CVPR 2023)
• Code: https://github.com/YaoleiQi/DSCNet

DWConv

• File: Convolution/DWConv.py
• Tags: Depthwise, Separable
• Paper: "Xception: Deep Learning with Depthwise Separable Convolutions" (CVPR 2017)
• Code: https://github.com/fchollet/deep-learning-models

GatedCNNBlock

• File: Convolution/GatedCNNBlock.py
• Tags: Dynamic
• Paper: "MambaOut Do We Really Need Mamba for Vision" (CVPR 2025)
• Code: https://github.com/yuweihao/MambaOut/tree/main

Gated Bottleneck Convolution (GBC)

• File: Convolution/Gated_Bottleneck_Conv.py
• Tags: Dynamic
• Paper: "SCSegamba Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures" (CVPR 2025)
• Code: https://github.com/Karl1109/SCSegamba

HDPA

• File: Convolution/HDPA.py
• Tags: Lightweight
• Paper: "MobileIE An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices" (ICCV 2025)
• Code: https://github.com/AVC2-UESTC/MobileIE

Half-Conv

• File: Convolution/Half-Conv.py
• Tags: Lightweight
• Paper: "Channel grouping vision transformer for lightweight fruit and vegetable recognition" (ESWA 2025)
• Code: https://github.com/Axboexx/CGViT

IDConv

• File: Convolution/IDConv.py
• Tags: Depthwise
• Paper: "InceptionNeXt: When Inception Meets ConvNeXt" (CVPR 2024)
• Code: https://github.com/sail-sg/inceptionnext

LDConv

• File: Convolution/LDConv.py
• Tags: Deformable
• Paper: "LDConv: Linear Deformable Convolution for Improving Convolutional Neural Networks" (IVC 2024)
• Code: https://github.com/Zhang-O-O/LDConv

LSConv

• File: Convolution/LSConv.py
• Tags: Large-Kernel
• Paper: "LSNet See Large, Focus Small" (CVPR 2025)
• Code: https://github.com/jameslahm/lsnet

LSNet

• File: Convolution/LSNet.py
• Tags: Large-Kernel
• Paper: "LSNet See Large, Focus Small" (CVPR 2025)
• Code: https://github.com/jameslahm/lsnet

MBRConv

• File: Convolution/MBRConv.py
• Tags: Lightweight
• Paper: "MobileIE An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices" (ICCV 2025)
• Code: https://github.com/AVC2-UESTC/MobileIE

MHCB

• File: Convolution/MHCB.py
• Tags: Lightweight
• Paper: "MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model" (AAAI 2026)
• Code: https://github.com/QianqianWang1325/MFmamba

MKIRA

• File: Convolution/MKIRA.py
• Tags: Depthwise
• Paper: "MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation" (ICCV 2025)
• Code:

MKP

• File: Convolution/MKP.py
• Tags: Lightweight
• Paper: "FBRT-YOLO Faster and Better for Real-Time Aerial Image Detection" (AAAI 2025)
• Code: https://github.com/galaxy-oss/FCM

MSGDC

• File: Convolution/MSGDC.py
• Tags: Dynamic
• Paper: "BHViT Binarized Hybrid Vision Transformer" (CVPR 2025)
• Code: https://github.com/IMRL/BHViT/tree/main

MobileNetV4

• File: Convolution/MobileNetV4.py
• Tags: Lightweight
• Paper: "MobileNetV4 -- Universal Models for the Mobile Ecosystem" (2024)
• Code: https://github.com/tensorflow/models

Moga Block

• File: Convolution/Moga_Block.py
• Tags: Dynamic
• Paper: "MogaNet: Multi-order Gated Aggregation Network" (ICLR 2024)
• Code: https://github.com/Westlake-AI/MogaNet

ODConv

• File: Convolution/ODConv.py
• Tags: Dynamic
• Paper: "Omni-Dimensional Dynamic Convolution" (ICLR 2022)
• Code: https://github.com/OSVAI/ODConv

OverLoCK

• File: Convolution/OverLoCK.py
• Tags: Large-Kernel
• Paper: "OverLoCK An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels" (CVPR 2025)
• Code: https://github.com/LMMMEng/OverLoCK/tree/main

PConv

• File: Convolution/PConv.py
• Tags: Lightweight
• Paper: "Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks" (CVPR 2023)
• Code: https://github.com/JierunChen/FasterNet

Pinwheel-shaped Conv

• File: Convolution/Pinwheel-shaped_Conv.py
• Tags: Dynamic
• Paper: "Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection" (AAAI 2025)
• Code: https://github.com/JN-Yang/PConv-SDloss-Data

PreCM

• File: Convolution/PreCM.py
• Tags: Dynamic
• Paper: "PreCM The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation" (arXiv 2025)
• Code: https://github.com/XinyuXu414

RFAConv

• File: Convolution/RFAConv.py
• Tags: Dynamic
• Paper: "RFAConv: Innovating Spatial Attention and Standard Convolutional Operation" (arXiv 2023)
• Code: https://github.com/Yongcheung/RFAConv

RefConv

• File: Convolution/RefConv.py
• Tags: Lightweight
• Paper: "RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets" (arXiv 2023)
• Code: https://github.com/okankop/RefConv

SAB

• File: Convolution/SAB.py
• Tags: Lightweight
• Paper: "Pluggable Style Representation Learning for Multi-Style Transfer" (ACCV 2024)
• Code: https://github.com/The-Learning-And-Vision-Atelier-LAVA/SaMST

SASE

• File: Convolution/SASE.py
• Tags: Depthwise
• Paper: "U-RWKV Lightweight medical image segmentation with direction-adaptive RWKV" (MICCAI 2025)
• Code: https://github.com/hbyecoding/U-RWKV

SCAM

• File: Convolution/SCAM.py
• Tags: Lightweight
• Paper: "(Common Acronym: Feature Enhancement Module. Found in"An Improved Lightweight Model for Protected Wildlife Detection" TGRS/PMC 2024, but generic)" (TGRS 2024)
• Code: https://github.com/yemu1138178251/FFCA-YOLO

ScConv

• File: Convolution/ScConv.py
• Tags: Dynamic
• Paper: "SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy" (CVPR 2023)
• Code: https://github.com/cheng-haha/ScConv

StripModule

• File: Convolution/StripModule.py
• Tags: Lightweight
• Paper: "Strip R-CNN：Large Strip Convolution for Remote Sensing Object Detection" (arXiv 2025)
• Code: https://github.com/HVision-NKU/Strip-R-CNN

TiedBlockConv

• File: Convolution/TiedBlockConv.py
• Tags: Lightweight
• Paper: "Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters" (AAAI 2021)
• Code: https://github.com/TiedBlockConv/TiedBlockConv

wConv2D

• File: Convolution/WConv2D.py
• Tags: Large-Kernel
• Paper: "Optimal Weighted Convolution for Classification and Denosing" (arXiv 2025)
• Code: https://github.com/cammarasana123/weightedConvolution2.0

Frequency

Converse2D

• File: Frequency/Converse2D.py
• Tags: FFT
• Paper: "Reverse Convolution and Its Applications to Image Restoration" (ICCV 2025)
• Code: https://github.com/cszn/ConverseNet

DCTSA

• File: Frequency/DCT_Spatial_Attention.py
• Tags: DCT
• Paper: "FSTA-SNNFrequency-Based Spatial-Temporal Attention Module for SpikingNeural Networks" (AAAI 2025)
• Code: https://github.com/yukairong/FSTA-SNN

DiSpAM

• File: Frequency/DiSpAM.py
• Tags: FFT
• Paper: "DarkIR Robust Low-Light Image Restoration" (CVPR 2025)
• Code: https://github.com/cidautai/DarkIR

DynamicFilter

• File: Frequency/DynamicFilter.py
• Tags: FFT
• Paper: "Dynamic Filter: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks" (AAAI 2024)
• Code: https://github.com/okojoalg/dfformer

EDFFN

• File: Frequency/EDFFN.py
• Tags: FFT
• Paper: "Efficient Visual State Space Model for Image Deblurring" (CVPR 2025)
• Code: https://github.com/kkkls/EVSSM

FCB

• File: Frequency/FCB.py
• Tags: FFT
• Paper: "Fourier Convolution Block with global receptive field for MRI reconstruction" (MIA 2025)
• Code: https://github.com/Haozhoong/FCB

FDConv

• File: Frequency/FDConv.py
• Tags: FFT
• Paper: "Frequency Dynamic Convolution for Dense Image Prediction" (CVPR 2025)
• Code: https://github.com/Linwei-Chen/FDConv

FFCM

• File: Frequency/FFCM.py
• Tags: FFT
• Paper: "SFHformer: When Fast Fourier Transform Meets Transformer for Image Restoration" (ECCV 2024)
• Code: https://github.com/deng-ai-lab/FADformer

FFTNetBlock

• File: Frequency/FFTNetBlock.py
• Tags: FFT
• Paper: "The FFT Strikes Again An Efficient Alternative to Self-Attention" (arXiv 2025)
• Code: https://github.com/jacobfa/fft

FMA

• File: Frequency/FMA.py
• Tags: FFT
• Paper: "SRConvNet A Transformer-Style ConvNet for Lightweight Image Super-Resolution" (IJCV 2025)
• Code: https://github.com/lifengcs/SRConvNet

FRCA

• File: Frequency/FRCA.py
• Tags: FFT
• Paper: "Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection" (2025)
• Code: https://github.com/JoshuaLPF/FreqSal

FSAS

• File: Frequency/FSAS.py
• Tags: FFT
• Paper: "Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring" (CVPR 2023)
• Code: https://github.com/LingshunKong/FSAS

F_Block

• File: Frequency/F_Block.py
• Tags: FFT
• Paper: "EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation" (arXiv 2024)
• Code: https://github.com/sheng-si/EMCAD

Fast_Fourier_Convolution

• File: Frequency/Fast_Fourier_Conv.py
• Tags: FFT
• Paper: "Fast Fourier Convolution" (NeurIPS 2020)
• Code: https://github.com/pkumivision/FFC

FourierUnit_modified

• File: Frequency/FourierUnit_modified.py
• Tags: FFT
• Paper: "Rethinking Fast Fourier Convolution in Image Inpainting" (ICCV 2023)
• Code: https://github.com/AndreyChu/Rethinking-FFC-in-Inpainting

Frequency-Aware Module(FAM)

• File: Frequency/Frequency-Aware_Module.py
• Tags: FFT
• Paper: "AFANet Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation" (arXiv 2025)
• Code: https://github.com/jarch-ma/AFANet

GFNet

• File: Frequency/GFNet.py
• Tags: FFT
• Paper: "Global Filter Networks for Image Classification" (NeurIPS 2021)
• Code: https://github.com/raoyongming/GFNet

GMWTConvs

• File: Frequency/GMWTConvs.py
• Tags: Wavelet
• Paper: "WaMaIR Image Restoration via Multiscale Wavelet Convolutions and Mamba-based Channel Modeling with Texture Enhancement" (PRCV 2025)
• Code:

HFP

• File: Frequency/HFP.py
• Tags: DCT
• Paper: "HS-FPN High Frequency and Spatial Perception FPN for Tiny Object Detection" (AAAI 2025)
• Code: https://github.com/ShiZican/HS-FPN

HWFE

• File: Frequency/HWFE.py
• Tags: Wavelet
• Paper: "MobileIE An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices" (ICCV 2025)
• Code: https://github.com/AVC2-UESTC/MobileIE

MDAF

• File: Frequency/MDAF.py
• Tags: Wavelet
• Paper: "SFFNet: A Wavelet-Based Spatial and Frequency Domain Fusion Network for Remote Sensing Segmentation" (arXiv2024)
• Code: https://github.com/yysdck/SFFNet

MSCA

• File: Frequency/MSCA.py
• Tags: DCT
• Paper: "RepVGG: Making VGG-style ConvNets Great Again" (CVPR 2021)
• Code: https://github.com/DingXiaoH/RepVGG

PWD

• File: Frequency/PWD.py
• Tags: Wavelet
• Paper: "GSFANet_Global_SpatialFrequency_Attention_Network_for_Infrared_Small_Target_Detection" (TGRS 2025)
• Code: https://github.com/dengfa02/GSFANet_IRSTD

RHDWT

• File: Frequency/RHDWT.py
• Tags: Wavelet
• Paper: "ASCNet_Asymmetric_Sampling_Correction_Network_for_Infrared_Image_Destriping" (TGRS 2025)
• Code: https://github.com/xdFai/ASCNet/tree/main

SFS-Conv

• File: Frequency/SFS-Conv.py
• Tags: FFT
• Paper: "Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection" (CVPR 2024)
• Code: https://github.com/Li-Qingyun/SFS-Conv

WA

• File: Frequency/WA.py
• Tags: Wavelet
• Paper: "Wavelet_and_Adaptive_Coordinate_Attention_Guided_Fine-Grained_Residual_Network_for_Image_Denoising" (TCSVT 2025)
• Code:

WMB

• File: Frequency/WMB.py
• Tags: Wavelet
• Paper: "Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement" (ACCV 2024)
• Code: https://github.com/Tan-Jun-Hao/WalMaFa

WTConv

• File: Frequency/WTConv.py
• Tags: Wavelet
• Paper: "Wavelet Convolutions for Large Receptive Fields" (ECCV 2024)
• Code: https://github.com/Babo1123/WTConv

Fusion

FFM

• File: Fusion/CFFormer_FFM.py
• Tags: Feature-Fusion
• Paper: "CFFormer_A_Cross-Fusion_Transformer_Framework_for_the_Semantic_Segmentation_of_Multisource_Remote_Sensing_Images" (TGRS 2025)
• Code: https://github.com/masurq/CFFormer

CGA

• File: Fusion/CGA.py
• Tags: Feature-Fusion
• Paper: "DEA-Net: Single Image Dehazing based on Detail Enhanced Convolution and Content-Guided Attention" (TIP 2024)
• Code: https://github.com/cecret3350/DEA-Net

Contrast Driven Feature Aggregation

• File: Fusion/Contrast_Driven_Feature_Aggregation.py
• Tags: Feature-Fusion
• Paper: "ConDSeg A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement" (AAAI 2025)
• Code: https://github.com/Mengqi-Lei/ConDSeg

FFM

• File: Fusion/DECS-Net_FFM.py
• Tags: Feature-Fusion
• Paper: "A dual encoder crack segmentation network with Haar wavelet-based high–low frequency attention" (ESWA 2024)
• Code: https://github.com/zZhiG/DECS-Net

EACM

• File: Fusion/EACM.py
• Tags: Feature-Fusion
• Paper: "Striking a better balance between segmentation performance and computational costs with a minimalistic network design" (ASOC 2025)
• Code: https://github.com/duweidai/BMIS

EFC

• File: Fusion/EFC.py
• Tags: Feature-Fusion
• Paper: "A Lightweight Fusion Strategy With Enhanced Interlayer Feature Correlation for Small Object Detection" (TGRS 2024)
• Code: https://github.com/nuliweixiao/EFC

EdgeGaussianAggregation

• File: Fusion/EdgeGaussianAggregation.py
• Tags: Feature-Fusion
• Paper: "LEGNet Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object Detection" (TCSVT 2025)
• Code: https://github.com/lwCVer/LEGNet

FEM

• File: Fusion/FEM.py
• Tags: Feature-Fusion
• Paper: "Common Acronym: Feature Enhancement Module. Found in"An Improved Lightweight Model for Protected Wildlife Detection" TGRS/PMC 2024, but generic)" (TGRS 2024)
• Code: https://github.com/yemu1138178251/FFCA-YOLO

FreqFusion

• File: Fusion/FreqFusion.py
• Tags: Feature-Fusion
• Paper: "FreqFusion: Frequency-Aware Fusion for Accurate LiDAR-Camera 3D Object Detection" (TPAMI 2024)
• Code: https://github.com/Linwei-Chen/FreqFusion

HFFE

• File: Fusion/HFFE.py
• Tags: Feature-Fusion
• Paper: "HAFNet_Hierarchical_Attention_Fusion_Network_for_Infrared_Small_Target_Detection" (TGRS 2025)
• Code: https://github.com/Wangtao-Bao/HAFNet

KernelSelectiveFusionAttention

• File: Fusion/KernelSelectiveFusionAttention.py
• Tags: Feature-Fusion
• Paper: "Dual selective fusion transformer network for hyperspectral image classification" (NN 2025)
• Code: https://github.com/YichuXu/DSFormer

MRFFE

• File: Fusion/MRFFE.py
• Tags: Feature-Fusion
• Paper: "Multiscale Gaussian Attention Mechanism for Tiny-Object Detection in Remote Sensing Images" (TGRS 2025)
• Code: https://github.com/cszzshi/MGAM

PPA

• File: Fusion/PPA.py
• Tags: Feature-Fusion
• Paper: "HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection" (arXiv2024)
• Code: https://github.com/zhengshuchen/HCFNet

RCM

• File: Fusion/RCM.py
• Tags: Feature-Fusion
• Paper: "MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping" (ECCV 2024)
• Code: https://github.com/woodfrog/MapTracker

SAFFM

• File: Fusion/SAFFM.py
• Tags: Feature-Fusion
• Paper: "Multi-scale Spatial-Spectral Attention Guided Fusion Network for Pansharpening" (2025)
• Code: https://github.com/MELiMZ/ssaff

SCPP

• File: Fusion/SCPP.py
• Tags: Feature-Fusion
• Paper: "GLVMamba_A_GlobalLocal_Visual_State-Space_Model_for_Remote_Sensing_Image_Segmentation" (TGRS 2025)
• Code: https://github.com/Tokisakiwlp/GLVMamba

Twin-branch feature extraction (TBFE)

• File: Fusion/Twin-branch_Feature_Extraction.py
• Tags: Feature-Fusion
• Paper: "A synergistic CNN-transformer network with pooling attention fusion for hyperspectral image classification" (DSP 2025)
• Code: https://github.com/chenpeng052/synergisticNet

UAFF

• File: Fusion/UAFF.py
• Tags: Feature-Fusion
• Paper: "Attention-guided hierarchical fusion U-Net for uncertainty-driven medical image segmentation" (INFFUS 2025)
• Code: https://github.com/AfsanaAhmedMunia/AHF-Fusion-U-Net

Normalization

BCN

• File: Normalization/BCN.py
• Tags: BN
• Paper: "BCN: Batch Channel Normalization for Image Classification" (arXiv 2023)
• Code: https://github.com/joe-siyuan-qiao/Batch-Channel-Normalization

Crossnorm&Selfnorm

• File: Normalization/Crossnorm&Selfnorm.py
• Tags: Adaptive
• Paper: "CrossNorm and SelfNorm for Generalization under Distribution Shifts" (ICCV 2021)
• Code: https://github.com/jocelyn-tang/CNSN

RepBN

• File: Normalization/RepBN.py
• Tags: BN
• Paper: "SLAB: Efficient Transformers with Simplified Linear Attention and Block-wise Reparameterization" (ICML 2024)
• Code: https://github.com/xinghaochen/SLAB

Resampling

DualPoolAttention

• File: Resampling/DualPoolAttention.py
• Tags: Pooling
• Paper: "MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model" (AAAI 2026)
• Code: https://github.com/QianqianWang1325/MFmamba

DySample

• File: Resampling/DySample.py
• Tags: Upsample
• Paper: "Learning to Upsample by Learning to Sample" (ICCV 2023)
• Code: https://github.com/tiny-smart/dysample

HaarWDownsampling

• File: Resampling/HaarWDownsampling.py
• Tags: Downsample
• Paper: "Haar Wavelet Downsampling: A Simple but Effective Downsampling Module for Semantic Segmentation" (Pattern Recognition 2023)
• Code: https://github.com/apple1986/HWD

PCDM

• File: Resampling/PCDM.py
• Tags: Downsample
• Paper: "Striking a better balance between segmentation performance and computational costs with a minimalistic network design" (ASOC 2025)
• Code: https://github.com/duweidai/BMIS

strip_pooling

• File: Resampling/Strip_pooling.py
• Tags: Pooling
• Paper: "Strip Pooling: Rethinking Spatial Pooling for Scene Parsing" (CVPR 2020)
• Code: https://github.com/houqb/SPNet

Sequence

AFT

• File: Sequence/AFT.py
• Tags: Transformer
• Paper: "An Attention Free Transformer" (arXiv 2021)
• Code: https://github.com/apple/ml-aft

AGCRN

• File: Sequence/AGCRN.py
• Tags: SSM
• Paper: "Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting" (AAAI 2019)
• Code: https://github.com/mhzhu87/AGCRN

ASSM

• File: Sequence/ASSM.py
• Tags: Mamba, SSM
• Paper: "MambaIRv2 Attentive State Space Restoration" (CVPR 2025)
• Code: https://github.com/csguoh/MambaIR/tree/main

assemFormer

• File: Sequence/AssemFormer.py
• Tags: Transformer
• Paper: "AssemFormer: Assemble-and-Distribute Attention for Efficient Image Super-Resolution" (arXiv 2024)
• Code: https://github.com/anthonyweidai/SvANet

Axial_attention

• File: Sequence/AxialAttention.py
• Tags: Transformer
• Paper: "Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation" (arXiv 2019)
• Code: https://github.com/csrhddlam/axial-deeplab

CLFT

• File: Sequence/CLFT.py
• Tags: Transformer
• Paper: "ABC: Attention with Bilinear Correlation for Infrared Small Target Detection" (ICME 2023)
• Code: https://github.com/PANPEIWEN/ABC

CSI

• File: Sequence/CSI.py
• Tags: Mamba, SSM
• Paper: "SAMamba Adaptive State Space Modeling with Hierarchical Vision for Infrared Small Target Detection" (INFFUS 2025)
• Code: https://github.com/zhengshuchen/SAMamba

CoAtNet

• File: Sequence/CoAtNet.py
• Tags: Transformer
• Paper: "CoAtNet: Marrying Convolution and Attention for All Data Sizes" (NeurIPS 2021)
• Code: https://github.com/chihyaoma/CoAtNet

Crossformer

• File: Sequence/Crossformer.py
• Tags: Transformer
• Paper: "CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention" (ICLR 2022)
• Code: https://github.com/cheerss/CrossFormer

EVS

• File: Sequence/EVS.py
• Tags: SSM
• Paper: "Efficient Visual State Space Model for Image Deblurring" (CVPR 2025)
• Code: https://github.com/kkkls/EVSSM

EfficientViMBlock

• File: Sequence/EfficientViMBlock.py
• Tags: Mamba
• Paper: "EfficientViM Efficient Vision Mamba with Hidden State Mixer based State Space Duality" (CVPR 2025)
• Code: https://github.com/mlvlab/EfficientViM

FFTTransformerEncoderBlock

• File: Sequence/FFTTransformerEncoderBlock.py
• Tags: Transformer
• Paper: "The FFT Strikes Again An Efficient Alternative to Self-Attention" (arXiv 2025)
• Code: https://github.com/jacobfa/fft

FRFN

• File: Sequence/FRFN.py
• Tags: Transformer
• Paper: "Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration" (CVPR 2024)
• Code: https://github.com/joshyZhou/AST

GLMambaAttention

• File: Sequence/GLMambaAttention.py
• Tags: Mamba
• Paper: "SC-MambaFew Few-shot learning based on Mamba and selective spatial-channel attention for bearing fault diagnosis" (Elsevier 2025)
• Code: https://github.com/giabao804/few-shot-mamba

HMHA

• File: Sequence/HMHA.py
• Tags: Transformer
• Paper: "Devil is in the Uniformity Exploring Diverse Learners within Transformer for Image Restoration" (ICCV 2025)
• Code: https://github.com/joshyZhou/HINT

MANO

• File: Sequence/MANO.py
• Tags: Transformer
• Paper: "Linear Attention with Global Context A Multipole Attention Mechanism for Vision and Physics" (ICCV 2025)
• Code: https://github.com/AlexColagrande/MANO

MOATransformer

• File: Sequence/MOATransformer.py
• Tags: Transformer
• Paper: "Aggregating Global Features into Local Vision Transformer" (ICPR 2022)
• Code: https://github.com/qhfan/MOA-Transformer

Manhattan_Self_Attention

• File: Sequence/Manhattan_Self_Attention.py
• Tags: SSM
• Paper: "RMT: Retentive Networks Meet Vision Transformers" (CVPR 2024)
• Code: https://github.com/qhfan/RMT

MobileViTAttention

• File: Sequence/MobileViTAttention.py
• Tags: Transformer
• Paper: "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer" (ICLR 2022)
• Code: https://github.com/apple/ml-cvnets

MobileViTv2

• File: Sequence/MobileViTv2.py
• Tags: Transformer
• Paper: "MobileViTv2: Efficient Separable Self-attention for Mobile Vision Transformers" (arXiv 2021)
• Code: https://github.com/apple/ml-cvnets

Mobile U-ViT

• File: Sequence/Mobile_U-ViT.py
• Tags: Transformer
• Paper: "Mobile U-ViT Revisiting large kernel and U-shaped ViT for efficient medical image segmentation" (ACM MM 2025)
• Code: https://github.com/FengheTan9/Mobile-U-ViT

Mona

• File: Sequence/Mona.py
• Tags: Transformer
• Paper: "Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks" (CVPR 2025)
• Code: https://github.com/Leiyi-Hu/mona

RAMiT

• File: Sequence/RAMiT.py
• Tags: Transformer
• Paper: "RAMiT: Relational Attention via Multi-scale Inter-Token Relations for Vision Transformers" (CVPR 2024)
• Code: https://github.com/rami0205/RAMiT

SAVSSM

• File: Sequence/SAVSSM.py
• Tags: SSM
• Paper: "SaMam Style-aware State Space Model for Arbitrary Image Style Transfer" (CVPR 2025)
• Code: https://github.com/Chernobyllight/SaMam

SBSAtt

• File: Sequence/SBSAtt.py
• Tags: Mamba
• Paper: "A Hybrid Transformer-Mamba Network for Single Image Deraining" (arXiv 2025)
• Code: https://github.com/sunshangquan/TransMamba

SEFN

• File: Sequence/SEFN.py
• Tags: SSM
• Paper: "SEM-Net Efficient Pixel Modelling for image inpainting with Spatially Enhanced SSM" (WACV 2025)
• Code: https://github.com/ChrisChen1023/SEM-Net

SFHformer

• File: Sequence/SFHformer.py
• Tags: Transformer
• Paper: "SFHformer: When Fast Fourier Transform Meets Transformer for Image Restoration" (ECCV 2024)
• Code: https://github.com/deng-ai-lab/FADformer

SPRSA

• File: Sequence/SPRSA.py
• Tags: Transformer
• Paper: "Cross Paradigm Representation and Alignment Transformer for Image Deraining" (ACM MM 2025)
• Code: https://github.com/zs1314/CPRAformer

SS-Conv-SSM

• File: Sequence/SS-Conv-SSM.py
• Tags: SSM
• Paper: "MedMamba Vision Mamba for Medical Image Classification" (arXiv 2025)
• Code: https://github.com/YubiaoYue/MedMamba

SequenceShuffleAttention

• File: Sequence/SequenceShuffleAttention.py
• Tags: Mamba
• Paper: "MaIR A Locality- and Continuity-Preserving Mamba for Image Restoration" (CVPR 2025)
• Code: https://github.com/XLearning-SCU/2025-CVPR-MaIR/tree/main

Super Token

• File: Sequence/Super_Token.py
• Tags: Transformer
• Paper: "Super Token Vision Transformer with Bi-level Global Context Adaptation" (CVPR 2023)
• Code: https://github.com/fudan-zvg/Super-Token-ViT

UVMB

• File: Sequence/UVMB.py
• Tags: SSM
• Paper: "U-shaped Vision Mamba for Single Image Dehazing" (arXiv 2025)
• Code: https://github.com/zzr-idam/UVM-Net

UniConvNet

• File: Sequence/UniConvNet.py
• Tags: Transformer
• Paper: "UniConvNet Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale" (ICCV 2025)
• Code: https://github.com/ai-paperwithcode/UniConvNet

ViP

• File: Sequence/ViP.py
• Tags: Transformer
• Paper: "Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition" (TPAMI 2022)
• Code: https://github.com/Andrew-Qibin/VisionPermutator

Utility

C-AdamW

• File: Utility/C-AdamW.py
• Tags: Training-Trick
• Paper: "Cautious Optimizers Improving Training with One Line of Code" (arXiv 2025)
• Code: https://github.com/kyleliang919/C-Optim

CBDE

• File: Utility/CBDE.py
• Tags: Training-Trick
• Paper: "Momentum Contrast for Unsupervised Visual Representation Learning (MoCo)" (CVPR 2020)
• Code: https://github.com/facebookresearch/moco