# Attention W-Net: Improved Skip Connections for better Representations

arXiv: https://arxiv.org/abs/2110.08811 · HTML: https://mlsanity.com/paper/2110.08811/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 17 Oct 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Context Encoding for Semantic Segmentation](https://mlsanity.com/paper/1803.08904/) (2018)
- [Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation](https://mlsanity.com/paper/1802.06955/) (2018)
- [DUNet: A deformable network for retinal vessel segmentation](https://mlsanity.com/paper/1811.01206/) (2018)
- [DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding](https://mlsanity.com/paper/1709.04696/) (2017)
- [SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation](https://mlsanity.com/paper/2004.03696/) (2020)
- [IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks](https://mlsanity.com/paper/1912.05763/) (2019)
- [Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping](https://mlsanity.com/paper/2002.11434/) (2020)
- [Attention Guided Network for Retinal Image Segmentation](https://mlsanity.com/paper/1907.12930/) (2019)
- [LadderNet: Multi-path networks based on U-Net for medical image segmentation](https://mlsanity.com/paper/1810.07810/) (2018)
- [Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels](https://mlsanity.com/paper/2103.03451/) (2021)
- [Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention](https://mlsanity.com/paper/2006.13011/) (2020)
- [Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation](https://mlsanity.com/paper/2105.09365/) (2021)

## Built on by (most cited first, 1 of 1)

- [Segmentation method of U-net sheet metal engineering drawing based on CBAM attention mechanism](https://mlsanity.com/paper/2209.14102/) (2022)

## Abstract (arXiv)

Segmentation of macro and microvascular structures in fundoscopic retinal images plays a crucial role in the detection of multiple retinal and systemic diseases, yet it is a difficult problem to solve. Most neural network approaches face several issues such as lack of enough parameters, overfitting and/or incompatibility between internal feature-spaces. We propose Attention W-Net, a new U-Net based architecture for retinal vessel segmentation to address these problems. In this architecture, we have two main contributions: Attention Block and regularisation measures. Our Attention Block uses attention between encoder and decoder features, resulting in higher compatibility upon addition. Our regularisation measures include augmentation and modifications to the ResNet Block used, which greatly prevent overfitting. We observe an F1 and AUC of 0.8407 and 0.9833 on the DRIVE and 0.8174 and 0.9865 respectively on the CHASE-DB1 datasets - a sizeable improvement over its backbone as well as competitive performance among contemporary state-of-the-art methods.