# Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

arXiv: https://arxiv.org/abs/2107.12461 · HTML: https://mlsanity.com/paper/2107.12461/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 26 Jul 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017)
- [ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data](https://mlsanity.com/paper/1904.00592/) (2019)
- [Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest](https://mlsanity.com/paper/1603.00275/) (2016)
- [MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation](https://mlsanity.com/paper/1902.04049/) (2019)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [The Importance of Skip Connections in Biomedical Image Segmentation](https://mlsanity.com/paper/1608.04117/) (2016)
- [Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks](https://mlsanity.com/paper/1904.10030/) (2019)
- [Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions](https://mlsanity.com/paper/1909.00166/) (2019)
- [KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations](https://mlsanity.com/paper/2006.04878/) (2020)
- [Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields](https://mlsanity.com/paper/1610.02177/) (2016)
- [Distance Map Loss Penalty Term for Semantic Segmentation](https://mlsanity.com/paper/1908.03679/) (2019)
- [Learning to Segment Skin Lesions from Noisy Annotations](https://mlsanity.com/paper/1906.03815/) (2019)
- [UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation](https://mlsanity.com/paper/2009.07501/) (2020)

## Built on by (most cited first, 12 of 12)

- [3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2209.15076/) (2022)
- [A Survey on Deep Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2206.00356/) (2022)
- [Masked Supervised Learning for Semantic Segmentation](https://mlsanity.com/paper/2210.00923/) (2022)
- [ConvNeXtv2 Fusion with Mask R-CNN for Automatic Region Based Coronary Artery Stenosis Detection for Disease Diagnosis](https://mlsanity.com/paper/2310.04749/) (2023)
- [WATUNet: A Deep Neural Network for Segmentation of Volumetric Sweep Imaging Ultrasound](https://mlsanity.com/paper/2311.10857/) (2023)
- [A State-of-the-art Survey of U-Net in Microscopic Image Analysis: from Simple Usage to Structure Mortification](https://mlsanity.com/paper/2202.06465/) (2022)
- [Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance](https://mlsanity.com/paper/2211.05364/) (2022)
- [DoubleU-NetPlus: A Novel Attention and Context Guided Dual U-Net with Multi-Scale Residual Feature Fusion Network for Semantic Segmentation of Medical Images](https://mlsanity.com/paper/2211.14235/) (2022)
- [Aortic root landmark localization with optimal transport loss for heatmap regression](https://mlsanity.com/paper/2407.04921/) (2024)
- [A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attention](https://mlsanity.com/paper/2407.18673/) (2024)
- [Self-Attention Diffusion Models for Zero-Shot Biomedical Image Segmentation: Unlocking New Frontiers in Medical Imaging](https://mlsanity.com/paper/2503.18170/) (2025)
- [Bridging spatial awareness and global context in medical image segmentation](https://mlsanity.com/paper/2512.06560/) (2025)

## Abstract (arXiv)

The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation. However, U-Net applies skip connections to merge semantically different low- and high-level convolutional features, resulting in not only blurred feature maps, but also over- and under-segmented target regions. To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation. The key rationale of Sharp U-Net is that instead of applying a plain skip connection, a depthwise convolution of the encoder feature map with a sharpening kernel filter is employed prior to merging the encoder and decoder features, thereby producing a sharpened intermediate feature map of the same size as the encoder map. Using this sharpening filter layer, we are able to not only fuse semantically less dissimilar features, but also to smooth out artifacts throughout the network layers during the early stages of training. Our extensive experiments on six datasets show that the proposed Sharp U-Net model consistently outperforms or matches the recent state-of-the-art baselines in both binary and multi-class segmentation tasks, while adding no extra learnable parameters. Furthermore, Sharp U-Net outperforms baselines that have more than three times the number of learnable parameters.