{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:43Z","timestamp":1777889863494,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02118","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22815-22825","source":"Crossref","is-referenced-by-count":0,"title":["Plug-in Feedback Self-Adaptive Attention in CLIP for Training-Free Open-Vocabulary Segmentation"],"prefix":"10.1109","author":[{"given":"Zhixiang","family":"Chi","sequence":"first","affiliation":[{"name":"University of Toronto"}]},{"given":"Yanan","family":"Wu","sequence":"additional","affiliation":[{"name":"China Agricultural University"}]},{"given":"Li","family":"Gu","sequence":"additional","affiliation":[{"name":"Concordia University"}]},{"given":"Huan","family":"Liu","sequence":"additional","affiliation":[{"name":"McMaster University"}]},{"given":"Ziqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Concordia University"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Concordia University"}]},{"given":"Konstantinos N","family":"Plataniotis","sequence":"additional","affiliation":[{"name":"University of Toronto"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00367"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning (ICML)","author":"Chen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00902"},{"key":"ref12","article-title":"Adapting to distribution shift by visual domain prompt generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chi","year":"2024"},{"key":"ref13","article-title":"Learning to adapt frozen clip for few-shot test-time domain adaptation","author":"Chi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"MMSegmentation Contributors","year":"2020","journal-title":"Mmsegmentation: Openmmlab semantic segmentation toolbox and benchmark"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref16","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"issue":"1\u201345","key":"ref17","first-page":"5","article-title":"The pascal visual object classes challenge 2012 (voc2012) development kit. Pattern Anal","volume":"2007","author":"Everingham","year":"2012","journal-title":"Stat. Model. Comput. Learn., Tech. Rep"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref19","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","author":"Guo","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref28","first-page":"1288812900","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref29","article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20047"},{"key":"ref32","first-page":"1925","article-title":"Refinenet: Multi-path refinement networks for highresolution semantic segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lin","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00571"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref38","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref41","article-title":"Test-time training with selfsupervision for generalization under distribution shifts","volume-title":"International conference on machine learning","author":"Sun","year":"2020"},{"key":"ref42","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wang","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00367"},{"key":"ref46","first-page":"332","article-title":"Distribution alignment for fully test-time adaptation with dynamic online data streams","volume-title":"European Conference on Computer Vision","author":"Wang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref48","article-title":"Clipself: Vision transformer distills itself for open-vocabulary dense prediction","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00159"},{"key":"ref50","article-title":"Clip-dinoiser: Teaching clip a few dino tricks","author":"Wysocza\u0144ska","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"ref52","article-title":"Demystifying clip data","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_10"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT57864.2024.10619241"},{"key":"ref56","article-title":"Bayes conditional distribution estimation for knowledge distillation based on conditional mutual information","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ye","year":"2020"},{"key":"ref57","article-title":"Towards undistillable models by minimizing conditional mutual information","author":"Ye","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref58","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3067100"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1616"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446086.pdf?arnumber=11446086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:22:14Z","timestamp":1777612934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02118","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}