Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
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.
Code (1)
Tasks
Domain AdaptationDomain GeneralizationPseudo LabelSemantic SegmentationSpecificityUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Generalized Source-free Domain Adaptation
Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is ava…
Domain AdaptationSource-Free Domain Adaptation1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track
OOD-CV challenge is an out-of-distribution generalization task. To solve this problem in object detection track, we propose a simple yet effective Generalize-then-Adapt (G&A) framework, which is composed of a two-stage d…
Domain AdaptationDomain Generalizationobject-detectionObject Detection+2A Comparison of Strategies for Source-Free Domain Adaptation
Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free…
Active LearningData AugmentationDomain AdaptationSource-Free Domain AdaptationA Comparison of Strategies for Source-Free Domain Adaptation
Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free…
Active LearningData AugmentationDomain AdaptationSource-Free Domain AdaptationSFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions
Domain adaptive visual object tracking under adverse weather conditions has garnered significant attention in recent years. Despite the impressive performance, existing methods heavily rely on the large-scale video frame…
Visual Object Tracking