Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation
This addresses domain shift problems in semantic segmentation for computer vision applications, representing an incremental improvement over existing domain adaptation and generalization methods.
The paper tackles domain generalized semantic segmentation by training a model on multiple source domains to generalize to unseen domains, proposing a meta-learning scheme with feature disentanglement and class-specific feature critics. The results show favorable performance against state-of-the-art methods on benchmark datasets.
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.