Unsupervised Domain Generalization by Learning a Bridge Across Domains
The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system. In this paper, different from most cross-domain works that utilize some (or full) source domain supervision, we approach a relatively new and very practical Unsupervised Domain Generalization (UDG) setup of having no training supervision in neither source nor target domains. Our approach is based on self-supervised learning of a Bridge Across Domains (BrAD) - an auxiliary bridge domain accompanied by a set of semantics preserving visual (image-to-image) mappings to BrAD from each of the training domains. The BrAD and mappings to it are learned jointly (end-to-end) with a contrastive self-supervised representation model that semantically aligns each of the domains to its BrAD-projection, and hence implicitly drives all the domains (seen or unseen) to semantically align to each other. In this work, we show how using an edge-regularized BrAD our approach achieves significant gains across multiple benchmarks and a range of tasks, including UDG, Few-shot UDA, and unsupervised generalization across multi-domain datasets (including generalization to unseen domains and classes).
Code (1)
Tasks
Domain GeneralizationSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Adaptation Across Extreme Variations using Unlabeled Domain Bridges
We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation. While deep domai…
Domain AdaptationObject RecognitionSemantic SegmentationUnsupervised Domain AdaptationTowards Unsupervised Domain Generalization
Domain generalization (DG) aims to help models trained on a set of source domains generalize better on unseen target domains. The performances of current DG methods largely rely on sufficient labeled data, which are usua…
Domain GeneralizationRepresentation LearningBridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization
Detectors often suffer from degraded performance, primarily due to the distributional gap between the source and target domains. This issue is especially evident in single-source domains with limited data, as models tend…
Domain GeneralizationCausal InferenceObject DetectionMulti-Target Domain Adaptation with Collaborative Consistency Learning
Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are onl…
Domain AdaptationMulti-target Domain AdaptationSemantic SegmentationUnsupervised Domain AdaptationUnsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains. In this paper, we present a novel approach that bridge…
DecoderDomain AdaptationRepresentation LearningUnsupervised Domain Adaptation