본문 바로가기

쓰기

 
발표자 김누리 
발표일자 2022-12-15 
저자 Harary, Sivan, et al. 
학회명 CVPR 2022 
논문지  
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).

    2024

      PAL: Program-aided Language Models
      2024.03.27
      발표자: 이재훈     발표일자: 2024-03-27     저자: Luyu Gao , Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, Graham Neubig     학회명: ICML 2023    
      Real-Time Evaluation in Online Continual Learning: A New Hope
      2024.02.28
      발표자: 이성준     발표일자: 2024-02-28     저자: Yasir Ghunaim, Adel Bibi. Kumail Alhamoud, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Ameya Prabhu, Philip H.S. Torrm, Bernard Ghanem     학회명: CVPR 2023    
      FlexiViT: One Model for All Patch Sizes
      2024.02.23
      발표자: 김영재     발표일자: 2024-02-23     저자: Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov, Mathilde Caron, Simon Kornblith, Xiaohua Zhai, Matthias Minderer, Michael Tschannen, Ibrahim Alabdulmohsin, Filip Pavetic     학회명: CVPR2023