Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation

TL;DR

This paper introduces a novel unsupervised domain adaptation method for semantic segmentation that treats 'stuff' and 'things' categories differently, improving alignment and stability, and achieves state-of-the-art results on benchmark datasets.

Contribution

The paper proposes a new approach that separately aligns stuff and thing categories, addressing their different appearance variations, and enhances adversarial training stability.

Findings

Achieved state-of-the-art segmentation accuracy on GTA5 to Cityscapes and SYNTHIA to Cityscapes tasks.

Demonstrated improved stability of adversarial training in domain adaptation.

Showed that separate alignment strategies for stuff and things are effective.

Abstract

We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling the domain shift issue. Based on the observation that stuff categories usually share similar appearances across images of different domains while things (i.e. object instances) have much larger differences, we propose to improve the semantic-level alignment with different strategies for stuff regions and for things: 1) for the stuff categories, we generate feature representation for each class and conduct the alignment operation from the target domain to the source domain; 2) for the thing categories, we generate feature representation for each individual instance and encourage the instance in the target domain to align with the most similar one in the source domain. In this way, the individual differences within thing categories will also be considered to alleviate over-alignment. In addition to our proposed method, we further reveal the reason why the current adversarial loss is often unstable in minimizing the distribution discrepancy and show that our method can help ease this issue by minimizing the most similar stuff and instance features between the source and the target domains. We conduct extensive experiments in two unsupervised domain adaptation tasks, i.e. GTA5 to Cityscapes and SYNTHIA to Cityscapes, and achieve the new state-of-the-art segmentation accuracy.