# A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation

arXiv: https://arxiv.org/abs/2108.07491 · HTML: https://mlsanity.com/paper/2108.07491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 17 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks](https://mlsanity.com/paper/1904.10030/) (2019)
- [Shape-Aware Organ Segmentation by Predicting Signed Distance Maps](https://mlsanity.com/paper/1912.03849/) (2019)
- [Deep Object Co-Segmentation](https://mlsanity.com/paper/1804.06423/) (2018)
- [Distance Map Loss Penalty Term for Semantic Segmentation](https://mlsanity.com/paper/1908.03679/) (2019)
- [A Distance Map Regularized CNN for Cardiac Cine MR Image Segmentation](https://mlsanity.com/paper/1901.01238/) (2019)
- [Distance transform regression for spatially-aware deep semantic segmentation](https://mlsanity.com/paper/1909.01671/) (2019)
- [Automatically Segmenting the Left Atrium from Cardiac Images Using Successive 3D U-Nets and a Contour Loss](https://mlsanity.com/paper/1812.02518/) (2018)
- [Fully-automatic segmentation of kidneys in clinical ultrasound images using a boundary distance regression network](https://mlsanity.com/paper/1901.01982/) (2019)

## Abstract (arXiv)

Image co-segmentation has attracted a lot of attentions in computer vision community. In this paper, we propose a new approach to image co-segmentation through introducing the dense connections into the decoder path of Siamese U-net and presenting a new edge enhanced 3D IOU loss measured over distance maps. Considering the rigorous mapping between the signed normalized distance map (SNDM) and the binary segmentation mask, we estimate the SNDMs directly from original images and use them to determine the segmentation results. We apply the Siamese U-net for solving this problem and improve its effectiveness by densely connecting each layer with subsequent layers in the decoder path. Furthermore, a new learning loss is designed to measure the 3D intersection over union (IOU) between the generated SNDMs and the labeled SNDMs. The experimental results on commonly used datasets for image co-segmentation demonstrate the effectiveness of our presented dense structure and edge enhanced 3D IOU loss of SNDM. To our best knowledge, they lead to the state-of-the-art performance on the Internet and iCoseg datasets.