diff --git a/segmentation_models_pytorch/base/heads.py b/segmentation_models_pytorch/base/heads.py
index fbc939ca..992f77d3 100644
--- a/segmentation_models_pytorch/base/heads.py
+++ b/segmentation_models_pytorch/base/heads.py
@@ -1,4 +1,5 @@
 import torch.nn as nn
+
 from .modules import Activation
 
 
@@ -10,7 +11,7 @@ def __init__(
             in_channels, out_channels, kernel_size=kernel_size, padding=kernel_size // 2
         )
         upsampling = (
-            nn.UpsamplingBilinear2d(scale_factor=upsampling)
+            nn.Upsample(mode="bilinear", scale_factor=upsampling, align_corners=True)
             if upsampling > 1
             else nn.Identity()
         )
diff --git a/segmentation_models_pytorch/decoders/deeplabv3/decoder.py b/segmentation_models_pytorch/decoders/deeplabv3/decoder.py
index 6a801a70..179985fd 100644
--- a/segmentation_models_pytorch/decoders/deeplabv3/decoder.py
+++ b/segmentation_models_pytorch/decoders/deeplabv3/decoder.py
@@ -31,7 +31,7 @@
 """
 
 from collections.abc import Iterable, Sequence
-from typing import Literal, List
+from typing import List, Literal
 
 import torch
 from torch import nn
@@ -105,7 +105,9 @@ def __init__(
         )
 
         scale_factor = 4 if output_stride == 16 and encoder_depth > 3 else 2
-        self.up = nn.UpsamplingBilinear2d(scale_factor=scale_factor)
+        self.up = nn.Upsample(
+            mode="bilinear", scale_factor=scale_factor, align_corners=True
+        )
 
         highres_in_channels = encoder_channels[2]
         highres_out_channels = 48  # proposed by authors of paper
diff --git a/segmentation_models_pytorch/losses/_functional.py b/segmentation_models_pytorch/losses/_functional.py
index 07efd7f4..74a63a8d 100644
--- a/segmentation_models_pytorch/losses/_functional.py
+++ b/segmentation_models_pytorch/losses/_functional.py
@@ -226,7 +226,7 @@ def wing_loss(
     idx_smaller = diff_abs < width
     idx_bigger = diff_abs >= width
 
-    loss[idx_smaller] = width * torch.log(1 + diff_abs[idx_smaller] / curvature)
+    loss[idx_smaller] = width * torch.log1p(diff_abs[idx_smaller] / curvature)
 
     C = width - width * math.log(1 + width / curvature)
     loss[idx_bigger] = loss[idx_bigger] - C