{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:15:23Z","timestamp":1775578523487,"version":"3.50.1"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["Z200002"],"award-info":[{"award-number":["Z200002"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2036"],"award-info":[{"award-number":["U19B2036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225601"],"award-info":[{"award-number":["62225601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovative Research Team of BUPT","award":["2023QNTD02"],"award-info":[{"award-number":["2023QNTD02"]}]},{"name":"MoE-CMCC","award":["MCM20190701"],"award-info":[{"award-number":["MCM20190701"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["CSC 202006470036"],"award-info":[{"award-number":["CSC 202006470036"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202206470055"],"award-info":[{"award-number":["202206470055"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX2020105"],"award-info":[{"award-number":["CX2020105"]}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX2022152"],"award-info":[{"award-number":["CX2022152"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3274593","type":"journal-article","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T20:26:54Z","timestamp":1683750414000},"page":"12068-12084","source":"Crossref","is-referenced-by-count":21,"title":["Making a Bird AI Expert Work for You and Me"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4081-3001","authenticated-orcid":false,"given":"Dongliang","family":"Chang","sequence":"first","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0408-2051","authenticated-orcid":false,"given":"Kaiyue","family":"Pang","sequence":"additional","affiliation":[{"name":"SketchX, CVSSP, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8372-5637","authenticated-orcid":false,"given":"Ruoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2699-0300","authenticated-orcid":false,"given":"Yujun","family":"Tong","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5908-3275","authenticated-orcid":false,"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[{"name":"SketchX, CVSSP, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9045-1339","authenticated-orcid":false,"given":"Jun","family":"Guo","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1483","article-title":"Understanding the role of adaptivity in machine teaching: The case of version space learners","author":"chen","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-4832-2828-0.50006-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref56","article-title":"Fine-grained visual classification of aircraft","author":"maji","year":"2013"},{"key":"ref15","article-title":"The curious layperson: Fine-grained image recognition without expert labels","author":"choudhury","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01469"},{"key":"ref53","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref11","first-page":"8928","article-title":"This looks like that: Deep learning for interpretable image recognition","author":"chen","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00402"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref17","first-page":"3450","article-title":"Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition","author":"deng","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.130"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439285"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01331-0"},{"key":"ref94","first-page":"1","article-title":"Rethinking soft labels for knowledge distillation: A Bias–variance tradeoff perspective","author":"zhou","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"ref46","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"li","year":"2022","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01067"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3240195"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00107"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298877"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00923"},{"key":"ref44","first-page":"11162","article-title":"ViT-NeT: Interpretable vision transformers with neural tree decoder","author":"kim","year":"2022","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01332"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref8","first-page":"1","article-title":"Explaining image classifiers by counterfactual generation","author":"chang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.598"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01131"},{"key":"ref4","article-title":"Flamingo: A visual language model for few-shot learning","author":"alayrac","year":"2022"},{"key":"ref3","article-title":"Attention cannot be an explanation","author":"akula","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s004260050047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref82","first-page":"1","article-title":"NBDT: Neural-backed decision tree","author":"wan","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref81","article-title":"The Caltech-UCSD birds-200–2011 dataset","author":"wah","year":"2011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00144"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00931"},{"key":"ref35","first-page":"24286","article-title":"One loss for all: Deep hashing with a single cosine similarity based learning objective","author":"hoe","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref79","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_16"},{"key":"ref37","article-title":"Language is not all you need: Aligning perception with language models","author":"huang","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-019-01846-w"},{"key":"ref31","first-page":"307","article-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics","volume":"13","author":"gutmann","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-10-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref74","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"sundararajan","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"ref77","author":"tukey","year":"1977","journal-title":"Exploratory Data Analysis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref76","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","author":"abelson","year":"1968","journal-title":"Theories of Cognitive Consistency A Sourcebook"},{"key":"ref1","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00066"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2996736"},{"key":"ref70","article-title":"SmoothGrad: Removing noise by adding noise","author":"smilkov","year":"2017"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"ref72","article-title":"Re-attention transformer for weakly supervised object localization","author":"su","year":"2022","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5214\/ans.0972.7531.200408"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref67","first-page":"1","article-title":"Restricting the flow: Information bottlenecks for attribution","author":"schulz","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref25","article-title":"Deep polarized network for supervised learning of accurate binary hashing codes","author":"fan","year":"2021","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_26"},{"key":"ref20","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"9521","DOI":"10.1109\/TPAMI.2021.3126668","article-title":"Progressive learning of category-consistent multi-granularity features for fine-grained visual classification","volume":"44","author":"du","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0146266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref28","first-page":"2376","article-title":"Counterfactual visual explanations","author":"goyal","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9280.02454"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.57967\/hf\/0222"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.344"},{"key":"ref61","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10122150.pdf?arnumber=10122150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:06:02Z","timestamp":1717693562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122150\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":94,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3274593","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":[[2023,10]]}}}