{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:23:25Z","timestamp":1740169405992,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1A2C2007884"],"award-info":[{"award-number":["2021R1A2C2007884"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) funded by Korean Government","doi-asserted-by":"publisher","award":["RS-2021-II211343","RS-2021-II212068","RS-2022-II220113","RS-2022-II220959"],"award-info":[{"award-number":["RS-2021-II211343","RS-2021-II212068","RS-2022-II220113","RS-2022-II220959"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3477454","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T17:25:48Z","timestamp":1728581148000},"page":"170295-170308","source":"Crossref","is-referenced-by-count":0,"title":["Debiased Learning via Composed Conceptual Sensitivity Regularization"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2176-917X","authenticated-orcid":false,"given":"Sunghwan","family":"Joo","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9257-6503","authenticated-orcid":false,"given":"Taesup","family":"Moon","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102305","article-title":"Analysis of the ISIC image datasets: Usage, benchmarks and recommendations","volume":"75","author":"Cassidy","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00338-7"},{"key":"ref3","first-page":"1","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","volume-title":"Proc. ICLR","author":"Hashimoto"},{"key":"ref4","first-page":"6781","article-title":"Just train twice: Improving group robustness without training group information","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu"},{"key":"ref5","first-page":"26484","article-title":"Correct-N-contrast: A contrastive approach for improving robustness to spurious correlations","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Zhang"},{"key":"ref6","first-page":"20673","article-title":"Learning from failure: Training debiased classifier from biased classifier","volume-title":"Proc. NeurIPS","author":"Nam"},{"article-title":"Spread spurious attribute: Improving worst-group accuracy with spurious attribute estimation","volume-title":"Proc. ICLR","author":"Nam","key":"ref7"},{"key":"ref8","first-page":"28448","article-title":"Simple and fast group robustness by automatic feature reweighting","volume-title":"Proc. ICML","author":"Qiu"},{"key":"ref9","first-page":"8847","article-title":"Large-scale methods for distributionally robust optimization","volume-title":"Proc. NeurIPS","author":"Levy"},{"key":"ref10","first-page":"2673","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV)","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/a:1022627411411"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30096"},{"key":"ref14","article-title":"Navigating neural space: Revisiting concept activation vectors to overcome directional divergence","author":"Pahde","year":"2022","journal-title":"arXiv:2202.03482"},{"article-title":"Concept gradient: Concept-based interpretation without linear assumption","volume-title":"Proc. ICLR","author":"Bai","key":"ref15"},{"key":"ref16","first-page":"336","article-title":"Simple data balancing achieves competitive worst-group-accuracy","volume-title":"Proc. 1st Conf. Causal Learn. Reasoning","volume":"177","author":"Idrissi"},{"article-title":"Last layer re-training is sufficient for robustness to spurious correlations","volume-title":"Proc. ICLR","author":"Kirichenko","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25088"},{"key":"ref19","first-page":"39584","article-title":"Change is hard: A closer look at subpopulation shift","volume-title":"Proc. ICML","author":"Yang"},{"key":"ref20","first-page":"37765","article-title":"Discover and cure: Concept-aware mitigation of spurious correlation","volume-title":"Proc. ICML","author":"Wu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01054"},{"article-title":"Distilling model failures as directions in latent space","volume-title":"Proc. ICLR","author":"Jain","key":"ref22"},{"key":"ref23","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00749"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.015"},{"key":"ref27","first-page":"10068","article-title":"Hard ImageNet: Segmentations for objects with strong spurious cues","volume-title":"Proc. NeurIPS","author":"Moayeri"},{"article-title":"Salient ImageNet: How to discover spurious features in deep learning?","volume-title":"Proc. ICLR","author":"Singla","key":"ref28"},{"key":"ref29","first-page":"41572","article-title":"Spuriosity rankings: Sorting data to measure and mitigate biases","volume-title":"Proc. NeurIPS","author":"Moayeri"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"article-title":"Learning deep features for scene recognition using places database","volume-title":"Proc. NeurIPS","author":"Zhou","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref33","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","first-page":"13567","article-title":"Explanations can be manipulated and geometry is to blame","volume-title":"Proc. NeurIPS","author":"Dombrowski"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov","key":"ref36"},{"article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. ICLR","author":"Loshchilov","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"volume-title":"The PyTorch Lightning Team","year":"2019","author":"Falcon","key":"ref39"},{"key":"ref40","first-page":"38516","article-title":"On feature learning in the presence of spurious correlations","volume-title":"Proc. NeurIPS","author":"Izmailov"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10713328.pdf?arnumber=10713328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:42:15Z","timestamp":1732668135000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10713328\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3477454","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}