paper-with-me

Papers

Unsupervised Domain Generalization by Learning a Bridge Across Domains

2021-12-04 · CVPR 2022 1 · Sivan Harary, Eli Schwartz, Assaf Arbelle, Peter Staar, Shady Abu-Hussein, Elad Amrani, Roei Herzig, Amit Alfassy, Raja Giryes, Hilde Kuehne, Dina Katabi, Kate Saenko, Rogerio Feris, Leonid Karlinsky

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).

📄 PDF Abstract BibTeX arXiv:2112.02300

Code (1)

leokarlin/brad 공식 구현 pytorch

Tasks

Domain GeneralizationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Adaptation Across Extreme Variations using Unlabeled Domain Bridges

2019-06-05 · Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin 외

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 Adaptation

Towards Unsupervised Domain Generalization

2021-07-13 · CVPR 2022 1 · Xingxuan Zhang, Linjun Zhou, Renzhe Xu, Peng Cui 외

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 Learning

Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization

2026-04-29 · Mingbo Hong, Feng Liu, Caroline Gevaert, George Vosselman 외 arxiv

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 Detection

Multi-Target Domain Adaptation with Collaborative Consistency Learning

2021-06-07 · CVPR 2021 1 · Takashi Isobe, Xu Jia, Shuaijun Chen, Jianzhong He 외

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 Adaptation

Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks

2019-02-17 · Jinyong Hou, Xuejie Ding, Jeremiah D. Deng, Stephen Cranefield

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