{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:10:38Z","timestamp":1777889438682,"version":"3.51.4"},"reference-count":60,"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"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00345809"],"award-info":[{"award-number":["RS-2024-00345809"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01896","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20390-20400","source":"Crossref","is-referenced-by-count":0,"title":["ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction"],"prefix":"10.1109","author":[{"given":"Juan","family":"Yeo","sequence":"first","affiliation":[{"name":"Gradudate School of Data Science, Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soonwoo","family":"Cha","sequence":"additional","affiliation":[{"name":"Gradudate School of Data Science, Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwoo","family":"Song","sequence":"additional","affiliation":[{"name":"Gradudate School of Data Science, Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunbin","family":"Jin","sequence":"additional","affiliation":[{"name":"Gradudate School of Data Science, Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taesup","family":"Kim","sequence":"additional","affiliation":[{"name":"Gradudate School of Data Science, Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01594"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00394"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref10","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref12","first-page":"16071616. PMLR","article-title":"Born again neural networks","volume-title":"International conference on machine learning","author":"Furlanello","year":"2018"},{"key":"ref13","article-title":"Openvocabulary detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Openvocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations","author":"Gu","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00110"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01072"},{"key":"ref19","article-title":"Open-vocabulary object detection upon frozen vision and language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kuo","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref21","volume-title":"Rethinking data augmentation: Self-supervision and self-distillation","author":"Lee","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref23","article-title":"Clip surgery for better explainability with enhancement in openvocabulary tasks","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Densevlm: A retrieval and decoupled alignment framework for open-vocabulary dense prediction","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref26","article-title":"Learning object-language alignments for open-vocabulary object detection","author":"Lin","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00726"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref30","first-page":"7086","article-title":"Image segmentation using text and Timo L\u00fcddecke and Alexander Ecker. Image segmentation using text","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"L\u00fcddecke","year":"2022"},{"key":"ref31","first-page":"23033","article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"International Conference on Machine Learning","author":"Luo","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref34","article-title":"Silc: Improving vision language pretraining with self-distillation","author":"Naeem","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref36","article-title":"Revisiting self-distillation","author":"Pham","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref38","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":"ref39","article-title":"Viewco: Discovering text-supervised segmentation masks via multi-view semantic consistency","author":"Ren","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01513"},{"key":"ref41","article-title":"Prompt-guided transformers for end-to-end open-vocabulary object detection","author":"Song","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref45","article-title":"Mosaic representation learning for self-supervised visual pre-training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wang","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref47","article-title":"CLIPSelf: Vision transformer distills itself for open-vocabulary dense prediction","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28428"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015565"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015628"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00047"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"}],"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\/11443367.pdf?arnumber=11443367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:13:41Z","timestamp":1777612421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01896","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}