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).
댓글 0
2023
Repair Is Nearly Generation: Multilingual Program Repair with LLMs
2023.11.08
발표자: 안지민
발표일자: 2023-11-08
저자: Harshit Joshi1 , Jose Cambronero ´ 2*, Sumit Gulwani2*, Vu Le2*, Ivan Radicek ˇ 3*, Gust Verbruggen4*
학회명: AAAI 2023
Weakly-Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor
2023.11.08
발표자: 최준수
발표일자: 2023-11-08
저자: Hyeokjun Kwon, Sung-Hoon Yoon, Kuk-jin Yoon
학회명: CVPR 2023
Complementary Relation Contrastive Distillation
2023.11.08
발표자: 이재준
발표일자: 2023-11-08
저자: Jinguo Zhu, Shixiang Tang, Dapeng Chen, Shijie Yu, Yakun Liu, Mingzhe Rong, Aijun Yang, Xiaohua Wang
학회명: CVPR 2021
LLM-BLENDER: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
2023.11.01
발표자: 나철원
발표일자: 2023-11-01
저자: Dongfu Jiang , Xiang Ren, Bill Yuchen Lin
학회명: ACL 2023
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts
2023.11.01
발표자: 이지형
발표일자: 2023-11-01
저자: Daniel Khashabi, Xinxi Lyu, Sewon Min, Lianhui Qin, Kyle Richardson, Sean Welleck, Hannaneh Hajishirzi, Tushar Khot, Ashish Sabharwal, Sameer Singh, Yejin Choi,
학회명: NAACL 2022
Dissecting Knowledge Distillation:An Exploration of its Inner Workings and Applications
2023.10.25
발표자: 안재한
발표일자: 2023-10-25
저자: Utkarsh Ojha, Yuheng Li, Yong Jae Lee
학회명: NeurIPS 2023
Superclass Learning with Representation Enhancement
2023.10.25
발표자: 이병준
발표일자: 2023-10-25
저자: Zeyu Gan, Suyun Zhao, Jinlong Kan, Liyuan Shang, Hong Chen, Cuiping Li
학회명: CVPR 2023
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases
2024.01.22
발표자: 양정안
발표일자: 2023-10-25
저자: Yingji Li, Mengnan Du, Xin Wang, Ying Wang
학회명: ACL 2023
Towards Unsupervised Domain Generalization for Face Anti-Spoofing
2023.10.11
발표자: 이진섭
발표일자: 2023-10-11
저자: Yuchen Liu¹, Yabo Chen², Mengran Gou³, Chun-Ting Huang³, Yaoming Wang¹, Wenrui Dai², Hongkai Xiong¹
학회명: 2023 ICCV
Scaling Language-Image Pre-training via Masking
2023.10.11
발표자: 장현민
발표일자: 2023-10-11
저자: Yanghao Li, Haoqi Fan, Fonghang Hu, Christoph Feichtenhofer, Kaiming He
학회명: CVPR 2023
Do Androids Laugh at Electric Sheep? Humor “Understanding” Benchmarks from The New Yorker Caption Contest
2023.10.11
발표자: 이재훈
발표일자: 2023-10-11
저자: Jack Hessel, Ana Marasovic, Jena D.Hwang, Lillian Lee, Jeff Da, Rowan Zellers, Robert Mankoff, Yejin Choi
학회명: 2023 ACL Best Paper Awards
CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
2023.10.04
발표자: 김효준
발표일자: 2023-10-04
저자: Tanay Dixit, Bhargavi Paranjape, Hannaneh Hajishirzi, Luke Zettlemoyer
학회명: 2022 EMNLP findings
LoRA: Low-Rank Adaptation of Large Language Models
2023.10.04
발표자: 김영재
발표일자: 2023-10-04
저자: Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen
학회명: ICLR 2022
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels
2023.10.04
발표자: 송경렬
발표일자: 2023-10-04
저자: Zixuan Ding1,4* Ao Wang2,3,4* Hui Chen2,3,† Qiang Zhang1 Pengzhang Liu5 Yongjun Bao5 Weipeng Yan5 Jungong Han6,7
학회명: CVPR 2023
논문지: CVPR 2023
Can Large Language Models Be an Alternative to Human Evaluation?
2023.09.20
발표자: 김호승
발표일자: 2023-09-20
저자: Cheng-Han Chiang, Hung-yi Lee
학회명: ACL 2023
Large Selective Kernel Network for Remote Sensing Object Detection
2023.09.20
발표자: 황성준
발표일자: 2023-09-20
Federated Learning from Pre-Trained Models: A Contrastive Learning Apporoach
2023.09.20
발표자: 강용훈
발표일자: 2023-09-20
저자: Yue Tan, Guodong Long, Jie Ma, Lu Liu, Tianyi Zhou, Jing Jiang
학회명: NeurIPS 2022
Conflict-based cross-view consistency for semi supervised semantic segmentation
2023.09.20
발표자: 장성인
발표일자: 2023-09-20
저자: Zicheng Wang
학회명: CVPR2023
Contrastive Curriculum Learning for Sequential User Behavior Modeling via Data Augmentation
2023.09.13
발표자: 김한별
발표일자: 2023-09-13
저자: Shuqing Bian, Wayne Xin Zhao, Kun Zhou, Jing Cai, Yancheng He, Cunxiang Yin, Ji-Rong Wen
학회명: CIKM 2021