{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T12:46:28Z","timestamp":1782564388682,"version":"3.54.5"},"reference-count":83,"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\/iccv51701.2025.01994","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21471-21481","source":"Crossref","is-referenced-by-count":1,"title":["FLOSS: Free Lunch in Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Yasser","family":"Benigmim","sequence":"first","affiliation":[{"name":"Inria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Fahes","sequence":"additional","affiliation":[{"name":"Inria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuan-Hung","family":"Vu","sequence":"additional","affiliation":[{"name":"Inria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrei","family":"Bursuc","sequence":"additional","affiliation":[{"name":"Inria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raoul","family":"de Charette","sequence":"additional","affiliation":[{"name":"Inria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3639996"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref4","article-title":"Zero-shot semantic segmentation","author":"Bucher","year":"2019","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref8","article-title":"Plot: Prompt learning with optimal transport for vision-language models","author":"Chen","year":"2023","journal-title":"ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2699184"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref14","article-title":"Test-time optimization for domain adaptive open vocabulary segmentation","author":"De Silva","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.547"},{"key":"ref17","volume-title":"The PASCAL Visual Object Classes Challenge2012 (VOC2012) Results","author":"Everingham","year":"2012"},{"key":"ref18","volume-title":"Uncertainty in deep learning","author":"Gal","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01067"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref22","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2022","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00495"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref25","article-title":"Mixed samples as probes for unsupervised model selection in domain adaptation","author":"Hu","year":"2023","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00297"},{"key":"ref27","article-title":"Renovating names in open-vocabulary segmentation benchmarks","author":"Huang","year":"2024","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Unsupervised prompt learning for vision-language models","author":"Huang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02244"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref32","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","author":"Kendall","year":"2017","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295387"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref36","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref40","article-title":"Visual classification via description from large language models","author":"Menon","year":"2023","journal-title":"ICLR"},{"key":"ref41","article-title":"Revisiting the calibration of modern neural networks","author":"Minderer","year":"2021","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02248"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref47","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref53","article-title":"Reco: Retrieve and co-segment for zero-shot transfer","author":"Shin","year":"2022","journal-title":"NeurIPS"},{"key":"ref54","article-title":"Testtime prompt tuning for zero-shot generalization in visionlanguage models","author":"Shu","year":"2022","journal-title":"NeurIPS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02235"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02190"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref58","article-title":"A closer look at the robustness of contrastive language-image pre-training (clip)","author":"Tu","year":"2023","journal-title":"NeurIPS"},{"key":"ref59","article-title":"An empirical study into what matters for calibrating vision-language models","author":"Tu","year":"2024","journal-title":"ICML"},{"key":"ref60","article-title":"Pop3d: Open-vocabulary 3d occupancy prediction from images","author":"Vobecky","year":"2023","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00262"},{"key":"ref62","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"Wang","year":"2021","journal-title":"ICLR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref64","article-title":"A hard-to-beat baseline for trainingfree CLIP-based adaptation","author":"Wang","year":"2024","journal-title":"ICLR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref69","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"NeurIPS"},{"key":"ref70","article-title":"Mano: Exploiting matrix norm for unsupervised accuracy estimation under distribution shifts","author":"Xie","year":"2024","journal-title":"NeurIPS"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref76","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref77","article-title":"Tipadapter: Training-free adaption of clip for few-shot classification","author":"Zhang","year":"2022","journal-title":"ECCV"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"}],"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\/11444095.pdf?arnumber=11444095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:03Z","timestamp":1777529463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444095\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01994","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}