Improving Image co-segmentation via Deep Metric Learning

TL;DR

This paper introduces a novel deep metric learning approach with IS-Triplet loss for image co-segmentation, improving pixel discrimination and segmentation performance efficiently.

Contribution

It proposes a new IS-Triplet loss for pixel-wise deep metric learning in image co-segmentation, with an efficient triple sampling strategy.

Findings

Enhanced pixel category discrimination in high-dimensional space.

Improved segmentation accuracy on SBCoseg and Internet datasets.

Fewer training epochs needed for effective segmentation.

Abstract

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.