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).

    2023

      What Can Human Sketches Do for Object Detection?
      2023.05.18
      발표자: 이재준     발표일자: 2023-05-17     저자: Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain, Subhadeep Koley, Tao Xiang ,Yi-Zhe Song     학회명: CVPR 2023    
      Stable Diffusion & Control Net
      2023.05.03
      발표자: 이진섭     발표일자: 2023-05-03     학회명: 2020 NeurIPS & 2023. 02. Arxiv    
      A graph placement methodology for fast chip design
      2023.04.12
      발표자: 지혜림     발표일자: 2023-04-12     저자: Azalia Mirhoseini1,4, Anna Goldie1,3,4, Mustafa Yazgan2, Joe Wenjie Jiang1, Ebrahim Songhori1, Shen Wang1, Young-Joon Lee2, Eric Johnson1, Omkar Pathak2, Azade Nazi1, Jiwoo Pak2, Andy Tong2, Kavya Srinivasa2, William Hang3, Emre Tuncer2, Quoc V. Le1, James Laudon1, Richard Ho2, Roger Carpenter2 & Jeff Dean     논문지: Nature 2021    
      Code Translation With Compiler Representation
      2023.04.12
      발표자: 최윤석     발표일자: 2023-04-12     저자: Marc Szafraniec, Baptiste Rozière, Hugh Leather, François Charton, Patrick Labatut, Gabriel Synnaeve     학회명: ICLR 2023