{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:29:52Z","timestamp":1781537392257,"version":"3.54.5"},"reference-count":118,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Planning Project of Zhejiang Province","award":["2024C01172"],"award-info":[{"award-number":["2024C01172"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3421340","type":"journal-article","created":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T17:39:30Z","timestamp":1719855570000},"page":"9221-9238","source":"Crossref","is-referenced-by-count":15,"title":["Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2545-2446","authenticated-orcid":false,"given":"Yue","family":"Han","sequence":"first","affiliation":[{"name":"Institute of Cyber-Systems and Control, Advanced Perception on Robotics and Intelligent Learning Lab (APRIL), Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-8090","authenticated-orcid":false,"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Cyber-Systems and Control, Advanced Perception on Robotics and Intelligent Learning Lab (APRIL), Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2684-0062","authenticated-orcid":false,"given":"Lu","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"Tiktok, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00919"},{"key":"ref9","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01384"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01083"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25129"},{"key":"ref16","article-title":"Frustratingly simple few-shot object detection","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"ref18","article-title":"Meta-learning with adaptive hyperparameters","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Baik"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19959"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref24","article-title":"Learning from few examples: A summary of approaches to few-shot learning","author":"Parnami","year":"2022"},{"key":"ref25","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00886"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00781"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_17"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00880"},{"key":"ref31","article-title":"FeLMi: Few shot learning with hard mixup","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Roy"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_43"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00245"},{"key":"ref35","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref37","first-page":"7115","article-title":"Tapnet: Neural network augmented with task-adaptive projection for few-shot learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00855"},{"key":"ref40","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01514"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00117"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01861"},{"key":"ref44","article-title":"Few-shot object detection via association and discrimination","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00311"},{"key":"ref46","article-title":"Generalized and discriminative few-shot object detection via svd-dictionary enhancement","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00325"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3125195"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01419"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00867"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3265865"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00789"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00974"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"ref55","article-title":"Intermediate prototype mining transformer for few-shot semantic segmentation","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00881"},{"key":"ref57","article-title":"Feature-proxy transformer for few-shot segmentation","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3155486"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013717"},{"key":"ref60","article-title":"Conditional networks for few-shot semantic segmentation","author":"Rakelly","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2992433"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"ref65","article-title":"Few-shot segmentation via cycle-consistent transformer","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115815"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00688"},{"key":"ref69","article-title":"One-shot instance segmentation","author":"Michaelis","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref73","article-title":"Hierarchical open-vocabulary universal image segmentation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref76","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref78","article-title":"Scaling open-vocabulary object detection","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Minderer"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00681"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00622"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref87","first-page":"71078","article-title":"CoDet: Co-occurrence guided region-word alignment for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref88","first-page":"1","article-title":"CLIPSelf: Vision transformer distills itself for open-vocabulary dense prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02254"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02005"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref94","article-title":"DST-Det: Simple dynamic self-training for open-vocabulary object detection","author":"Xu","year":"2023"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref96","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref98","article-title":"A comprehensive survey on pretrained foundation models: A history from BERT to ChatGPT","author":"Zhou","year":"2023"},{"key":"ref99","article-title":"COCA: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3434373"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1385-0"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref106","article-title":"Accuracy of segment-anything model (SAM) in medical image segmentation tasks","author":"He","year":"2023"},{"key":"ref107","article-title":"Medical SAM adapter: Adapting segment anything model for medical image segmentation","author":"Wu","year":"2023"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/bibm58861.2023.10386032"},{"key":"ref109","article-title":"Personalize segment anything model with one shot","author":"Zhang","year":"2023"},{"key":"ref110","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_12"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref116","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_25"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10579052.pdf?arnumber=10579052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:29:51Z","timestamp":1732667391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10579052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":118,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3421340","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":[[2024,12]]}}}