{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T06:19:37Z","timestamp":1775888377363,"version":"3.50.1"},"reference-count":166,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62372405"],"award-info":[{"award-number":["62372405"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tpami.2024.3387116","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T18:14:27Z","timestamp":1712772867000},"page":"6858-6872","source":"Crossref","is-referenced-by-count":59,"title":["Prototype-Based Semantic Segmentation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5475-1473","authenticated-orcid":false,"given":"Tianfei","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Computer Science, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"CCAI, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00381"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref13","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref15","article-title":"CLUSTSEG: Clustering for universal segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref20","volume-title":"Pattern Classification and Scene Analysis","volume":"3","author":"Duda","year":"1973"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(73)90017-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.8259522"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_42"},{"key":"ref25","article-title":"Few-shot semantic segmentation with prototype learning","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Dong"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_18"},{"key":"ref28","article-title":"Rethinking softmax cross-entropy loss for adversarial robustness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553531"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref33","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04003-0_8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.09.048"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref47","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2737535"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00770"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00960"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3239194"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00705"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00710"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00714"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16294"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.539"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref67","article-title":"Pyramid attention network for semantic segmentation","author":"Li","year":"2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055780"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00366"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3168530"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102599"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.492"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00692"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.392"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_29"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01368"},{"key":"ref83","article-title":"FasterSeg: Searching for faster real-time semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00934"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"ref87","article-title":"Uncovering prototypical knowledge for weakly open-vocabulary semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587462"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_26"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.131"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248004"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.405"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00940"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00733"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00743"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115815"},{"key":"ref99","article-title":"Adaptive masked weight imprinting for few-shot segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Siam"},{"key":"ref100","article-title":"Visual recognition with deep nearest centroids","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2017.66"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00904"},{"key":"ref103","volume-title":"Human Problem Solving","volume":"104","author":"Newell","year":"1972"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-1994-7104"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1961.287775"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809682"},{"key":"ref108","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Friedman","year":"2009"},{"issue":"9","key":"ref109","article-title":"Pattern recognition","volume":"128","author":"Bishop","year":"2006","journal-title":"Mach. Learn."},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.142"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(98)00030-7"},{"key":"ref112","first-page":"423","article-title":"Generalized learning vector quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sato"},{"key":"ref113","first-page":"513","article-title":"Neighbourhood components analysis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goldberger"},{"key":"ref114","first-page":"412","article-title":"Learning a nonlinear embedding by preserving class neighbourhood structure","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Salakhutdinov"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/5.58326"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.120"},{"key":"ref118","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00366"},{"key":"ref120","article-title":"DeepNCM: Deep nearest class mean classifiers","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Guerriero"},{"key":"ref121","article-title":"Hyperspherical prototype networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mettes"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"ref123","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12084-3_9"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref126","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3332435"},{"key":"ref129","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref130","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref131","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref132","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref135","first-page":"3853","article-title":"CliqueCNN: Deep unsupervised exemplar learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bautista"},{"key":"ref136","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"ref139","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref140","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Asano"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"ref142","article-title":"Clustering-friendly representation learning via instance discrimination and feature decorrelation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tao"},{"key":"ref143","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00761"},{"key":"ref145","first-page":"31360","article-title":"GMMSeg: Gaussian mixture based generative semantic segmentation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref146","article-title":"The need for biases in learning generalizations","author":"Mitchell","year":"1980"},{"key":"ref147","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref150","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cuturi"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.2307\/2314570"},{"key":"ref152","first-page":"1961","article-title":"Near-linear time approximation algorithms for optimal transport via sinkhorn iteration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Altschuler"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref156","first-page":"7281","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_36"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00939"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00909"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00685"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176342503"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10666888\/10496237.pdf?arnumber=10496237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:46:18Z","timestamp":1725684378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":166,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3387116","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}