Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
This work addresses the need for domain adaptation in scenarios where source data is unavailable, which is crucial for real-world deployment in changing environments.
The paper tackles the problem of source-free domain adaptation for semantic segmentation by splitting it into domain generalization and target adaptation, achieving superior performance on GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes benchmarks compared to prior non-source-free methods.
Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios demanding source-free adaptation. In this work, we enable source-free DA by partitioning the task into two: a) source-only domain generalization and b) source-free target adaptation. Towards the former, we provide theoretical insights to develop a multi-head framework trained with a virtually extended multi-source dataset, aiming to balance generalization and specificity. Towards the latter, we utilize the multi-head framework to extract reliable target pseudo-labels for self-training. Additionally, we introduce a novel conditional prior-enforcing auto-encoder that discourages spatial irregularities, thereby enhancing the pseudo-label quality. Experiments on the standard GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes benchmarks show our superiority even against the non-source-free prior-arts. Further, we show our compatibility with online adaptation enabling deployment in a sequentially changing environment.