{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:15:23Z","timestamp":1787937323616,"version":"build-2784847793"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276108"],"award-info":[{"award-number":["62276108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3678362","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:53:25Z","timestamp":1775159605000},"page":"4425-4439","source":"Crossref","is-referenced-by-count":4,"title":["WeakTr: Exploring Plain Vision Transformer for Weakly-Supervised Semantic Segmentation"],"prefix":"10.1109","volume":"35","author":[{"given":"Lianghui","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingyue","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0322-4582","authenticated-orcid":false,"given":"Jiemin","family":"Fang","sequence":"additional","affiliation":[{"name":"Huawei Inc.,, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6021-1358","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Hao","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4582-7488","authenticated-orcid":false,"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6732-7823","authenticated-orcid":false,"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3246102"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"ref7","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.7062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref14","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-00296-0","article-title":"Pearson correlation coefficient","author":"Cohen","year":"2009","journal-title":"Noise Reduction in Speech Processing"},{"key":"ref17","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref18","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref19","first-page":"1","article-title":"How to train your ViT? Data, augmentation, and regularization in vision transformers","volume":"2022","author":"Steiner","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref22","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref23","first-page":"8536","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Han"},{"key":"ref24","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arazo"},{"key":"ref25","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103800"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00064"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3065-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"ref35","first-page":"547","article-title":"Self-erasing network for integral object attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Hou"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.17"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"ref40","first-page":"109","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Krahenbuhl"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_21"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00719"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00691"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01586-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_19"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00302"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_26"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01090"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00339"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00345"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_15"},{"key":"ref58","first-page":"293","article-title":"Phase concentration and shortcut suppression for weakly supervised semantic segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Kwon"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_23"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00918"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01402"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02815"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02817"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref65","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00325"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00364"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00425"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01639"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02267"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447893"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28584"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00692"},{"issue":"2","key":"ref81","first-page":"1447","article-title":"Uncertainty estimation via response scaling for pseudo-mask noise mitigation in weakly-supervised semantic segmentation","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"36","author":"Li"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref83","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref84","first-page":"4015","article-title":"Segment anything","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Kirillov"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02224-2"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00058"},{"key":"ref87","article-title":"Segment anything model (SAM) enhanced pseudo labels for weakly supervised semantic segmentation","volume-title":"Proc. NeurIPS Workshop (ICBINB)","author":"Chen"},{"key":"ref88","article-title":"An alternative to WSSS? An empirical study of the segment anything model (SAM) on weakly-supervised semantic segmentation problems","author":"Sun","year":"2023","journal-title":"arXiv:2305.01586"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01844"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680960"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref92","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00306"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_26"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_14"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11473328.pdf?arnumber=11473328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:29:58Z","timestamp":1777609798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11473328\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3678362","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}