IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels

TL;DR

This paper introduces IDPL, a novel unsupervised domain adaptation method for image segmentation that dynamically generates pseudo labels and adaptively divides the target domain into subdomains to improve segmentation accuracy, especially for difficult categories.

Contribution

The paper proposes a new intra-subdomain adaptation adversarial learning framework with dynamic pseudo labels and subdomain division, enhancing segmentation performance over existing methods.

Findings

Significant improvement in segmentation accuracy for difficult categories.

Effective dynamic pseudo label generation based on class and instance matching.

Enhanced class-level feature alignment through subdomain adversarial learning.

Abstract

Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this end, in this paper, Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed. The whole process consists of 3 steps: Firstly, the instance-level pseudo label dynamic generation module is proposed, which fuses the class matching information in global classes and local instances, thus adaptively generating the optimal threshold for each class, obtaining high-quality pseudo labels. Secondly, the subdomain classifier module based on instance confidence is constructed, which can dynamically divide the target domain into easy and difficult subdomains according to the relative proportion of easy and difficult instances. Finally, the subdomain adversarial learning module based on self-attention is proposed. It uses multi-head self-attention to confront the easy and difficult subdomains at the class level with the help of generated high-quality pseudo labels, so as to focus on mining the features of difficult categories in the high-entropy region of target domain images, which promotes class-level conditional distribution alignment between the subdomains, improving the segmentation performance of difficult categories. For the difficult categories, the experimental results show that the performance of IDPL is significantly improved compared with other latest mainstream methods.