# Redefining the Down-Sampling Scheme of U-Net for Precision Biomedical Image Segmentation

arXiv: https://arxiv.org/abs/2602.19412 · HTML: https://mlsanity.com/paper/2602.19412/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation](https://mlsanity.com/paper/2402.05079/) (2024)
- [Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation](https://mlsanity.com/paper/2303.10323/) (2023)
- [Strip Pooling: Rethinking Spatial Pooling for Scene Parsing](https://mlsanity.com/paper/2003.13328/) (2020)
- [AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling](https://mlsanity.com/paper/2111.00772/) (2021)
- [LIP: Local Importance-based Pooling](https://mlsanity.com/paper/1908.04156/) (2019)
- [Detail-Preserving Pooling in Deep Networks](https://mlsanity.com/paper/1804.04076/) (2018)
- [Refining activation downsampling with SoftPool](https://mlsanity.com/paper/2101.00440/) (2021)
- [Learning strides in convolutional neural networks](https://mlsanity.com/paper/2202.01653/) (2022)
- [Mask Propagation for Efficient Video Semantic Segmentation](https://mlsanity.com/paper/2310.18954/) (2023)
- [S3Pool: Pooling with Stochastic Spatial Sampling](https://mlsanity.com/paper/1611.05138/) (2016)
- [MLP Can Be A Good Transformer Learner](https://mlsanity.com/paper/2404.05657/) (2024)
- [LiftPool: Bidirectional ConvNet Pooling](https://mlsanity.com/paper/2104.00996/) (2021)
- [Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System](https://mlsanity.com/paper/2207.07827/) (2022)

## Abstract (arXiv)

U-Net architectures have been instrumental in advancing biomedical image segmentation (BIS) but often struggle with capturing long-range information. One reason is the conventional down-sampling techniques that prioritize computational efficiency at the expense of information retention. This paper introduces a simple but effective strategy, we call it Stair Pooling, which moderates the pace of down-sampling and reduces information loss by leveraging a sequence of concatenated small and narrow pooling operations in varied orientations. Specifically, our method modifies the reduction in dimensionality within each 2D pooling step from frac14 to frac12. This approach can also be adapted for 3D pooling to preserve even more information. Such preservation aids the U-Net in more effectively reconstructing spatial details during the up-sampling phase, thereby enhancing its ability to capture long-range information and improving segmentation accuracy. Extensive experiments on three BIS benchmarks demonstrate that the proposed Stair Pooling can increase both 2D and 3D U-Net performance by an average of 3.8% in Dice scores. Moreover, we leverage the transfer entropy to select the optimal down-sampling paths and quantitatively show how the proposed Stair Pooling reduces the information loss.