# Improving Image co-segmentation via Deep Metric Learning

arXiv: https://arxiv.org/abs/2103.10670 · HTML: https://mlsanity.com/paper/2103.10670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://mlsanity.com/paper/1611.09326/) (2016)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [Ranked List Loss for Deep Metric Learning](https://mlsanity.com/paper/1903.03238/) (2019)
- [Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning](https://mlsanity.com/paper/1804.03131/) (2018)
- [Semantic Instance Segmentation via Deep Metric Learning](https://mlsanity.com/paper/1703.10277/) (2017)
- [Deep Object Co-Segmentation](https://mlsanity.com/paper/1804.06423/) (2018)
- [Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop](https://mlsanity.com/paper/1512.05227/) (2015)
- [A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning](https://mlsanity.com/paper/1904.08720/) (2019)
- [A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI](https://mlsanity.com/paper/1604.00494/) (2016)
- [Deep Metric Learning by Online Soft Mining and Class-Aware Attention](https://mlsanity.com/paper/1811.01459/) (2018)
- [Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification](https://mlsanity.com/paper/1710.00478/) (2017)

## Abstract (arXiv)

Deep Metric Learning (DML) is helpful in computer vision tasks. In this paper, we firstly introduce DML into image co-segmentation. We propose a novel Triplet loss for Image Segmentation, called IS-Triplet loss for short, and combine it with traditional image segmentation loss. Different from the general DML task which learns the metric between pictures, we treat each pixel as a sample, and use their embedded features in high-dimensional space to form triples, then we tend to force the distance between pixels of different categories greater than of the same category by optimizing IS-Triplet loss so that the pixels from different categories are easier to be distinguished in the high-dimensional feature space. We further present an efficient triple sampling strategy to make a feasible computation of IS-Triplet loss. Finally, the IS-Triplet loss is combined with 3 traditional image segmentation losses to perform image segmentation. We apply the proposed approach to image co-segmentation and test it on the SBCoseg dataset and the Internet dataset. The experimental result shows that our approach can effectively improve the discrimination of pixels' categories in high-dimensional space and thus help traditional loss achieve better performance of image segmentation with fewer training epochs.