{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:07:00Z","timestamp":1749269220661,"version":"3.41.0"},"reference-count":120,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["NRF-P2024-001"],"award-info":[{"award-number":["NRF-P2024-001"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3549300","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:39:08Z","timestamp":1741628348000},"page":"5445-5459","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Explore Sample Relationships"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2990-505X","authenticated-orcid":false,"given":"Zhi","family":"Hou","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0761-7893","authenticated-orcid":false,"given":"Baosheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9002-1029","authenticated-orcid":false,"given":"Chaoyue","family":"Wang","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3180-0484","authenticated-orcid":false,"given":"Yibing","family":"Zhan","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref3","first-page":"1","article-title":"Long-tailed recognition by routing diverse distribution-aware experts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref5","first-page":"22405","article-title":"Swad: Domain generalization by seeking flat minima","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cha"},{"key":"ref6","first-page":"1","article-title":"Generalizing across domains via cross-gradient training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shankar"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00517"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref10","first-page":"7032","article-title":"Learning to model the tail","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00378"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00440"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref15","first-page":"5212","article-title":"A causal view of compositional zero-shot recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Atzmon"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref18","first-page":"5102","article-title":"Domain agnostic learning with disentangled representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"article-title":"Invariant risk minimization","year":"2019","author":"Arjovsky","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref25","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref26","first-page":"1","article-title":"Regionvit: Regional-to-local attention for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00711"},{"article-title":"Batchformerv2: Exploring sample relationships for dense representation learning","year":"2022","author":"Hou","key":"ref29"},{"key":"ref30","first-page":"1","article-title":"Learning to propagate labels: Transductive propagation network for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref31","first-page":"4005","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"article-title":"Mini-batch graphs for robust image classification","year":"2021","author":"Mondal","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00647"},{"article-title":"Compas: Representation learning with compositional part sharing for few-shot classification","year":"2021","author":"He","key":"ref34"},{"key":"ref35","first-page":"28742","article-title":"Self-attention between datapoints: Going beyond individual input-output pairs in deep learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kossen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref39","first-page":"872","article-title":"What is the effect of importance weighting in deep learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Byrd"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00030"},{"key":"ref47","first-page":"2178","article-title":"Generalizing from several related classification tasks to a new unlabeled sample","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Blanchard"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3195549"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/628"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"article-title":"Zero-shot learning with semantic output codes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Palatucci","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00111"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_33"},{"key":"ref55","first-page":"998","article-title":"Metareg: Towards domain generalization using meta-regularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Balaji"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00621"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_18"},{"key":"ref58","first-page":"7728","article-title":"Efficient domain generalization via common-specific low-rank decomposition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Piratla"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"Bahdanau","key":"ref59"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref60"},{"key":"ref61","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"Zhu","key":"ref63"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref66","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref70","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"article-title":"Beit: BERT pre-training of image transformers","year":"2021","author":"Bao","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref74","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref76","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref78","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"10","key":"ref80","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"The Handbook Brain Theory Neural Netw."},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref82","first-page":"4175","article-title":"Balanced meta-softmax for long-tailed visual recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00075"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"ref87","first-page":"1","article-title":"Decoupling representation and classifier for long-tailed recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kang"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.32"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00369"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.208"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"article-title":"Transfer-learning-library","year":"2020","author":"Jiang","key":"ref96"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref98","first-page":"1","article-title":"Domain generalization with mixstyle","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"article-title":"Improved baselines with momentum contrastive learning","year":"2020","author":"Chen","key":"ref99"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref102","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref103","first-page":"1","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00100"},{"key":"ref108","first-page":"1","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_36"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"article-title":"Detectron2","year":"2019","author":"Wu","key":"ref112"},{"key":"ref113","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"article-title":"PyTorch image models","year":"2019","author":"Wightman","key":"ref114"},{"key":"ref115","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (rex)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krueger"},{"key":"ref116","first-page":"1","article-title":"VisDA: The visual domain adaptation challenge","author":"Peng","year":"2017"},{"key":"ref117","first-page":"7404","article-title":"Bridging theory and algorithm for domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00090"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10918791.pdf?arnumber=10918791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:41:54Z","timestamp":1749231714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10918791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":120,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3549300","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}