Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation

TL;DR

This paper introduces a meta-learning approach with feature disentanglement and class-specific critics to improve domain generalization in semantic segmentation, achieving state-of-the-art results on benchmark datasets.

Contribution

It proposes a novel meta-learning scheme with feature disentanglement and class-specific critics for domain-generalized semantic segmentation, which is a new approach in this area.

Findings

Outperforms existing methods on benchmark datasets.

Demonstrates robustness across unseen domains.

Effective in learning domain-invariant features.

Abstract

How to handle domain shifts when recognizing or segmenting visual data across domains has been studied by learning and vision communities. In this paper, we address domain generalized semantic segmentation, in which the segmentation model is trained on multiple source domains and is expected to generalize to unseen data domains. We propose a novel meta-learning scheme with feature disentanglement ability, which derives domain-invariant features for semantic segmentation with domain generalization guarantees. In particular, we introduce a class-specific feature critic module in our framework, enforcing the disentangled visual features with domain generalization guarantees. Finally, our quantitative results on benchmark datasets confirm the effectiveness and robustness of our proposed model, performing favorably against state-of-the-art domain adaptation and generalization methods in segmentation.