{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T16:57:32Z","timestamp":1783357052260,"version":"3.54.6"},"reference-count":225,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFD2001100"],"award-info":[{"award-number":["2024YFD2001100"]}]},{"name":"National Key R&D Program of China","award":["2024YFE0214300"],"award-info":[{"award-number":["2024YFE0214300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62162008"],"award-info":[{"award-number":["62162008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guizhou Provincial Science and Technology Projects","award":["[2024]002"],"award-info":[{"award-number":["[2024]002"]}]},{"name":"Guizhou Provincial Science and Technology Projects","award":["CXTD[2023]027"],"award-info":[{"award-number":["CXTD[2023]027"]}]},{"name":"Guizhou Province Youth Science and Technology Talent Project","award":["[2024]317"],"award-info":[{"award-number":["[2024]317"]}]},{"name":"Guiyang Guian Science and Technology Talent Training Project","award":["[2024] 2-15"],"award-info":[{"award-number":["[2024] 2-15"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tai.2025.3526138","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T15:06:26Z","timestamp":1736262386000},"page":"1540-1560","source":"Crossref","is-referenced-by-count":6,"title":["From Global to Hybrid: A Review of Supervised Deep Learning for 2-D Image Feature Representation"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0217-2353","authenticated-orcid":false,"given":"Xinyu","family":"Dong","sequence":"first","affiliation":[{"name":"State Key Laboratory of Public Big Data, college of computer science, Guizhou University, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6269-0196","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, college of computer science, Guizhou University, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Deng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, college of computer science, Guizhou University, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9392-1375","authenticated-orcid":false,"given":"Zhenguo","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3710-8739","authenticated-orcid":false,"given":"Weijian","family":"Ruan","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1633-7575","authenticated-orcid":false,"given":"Wu","family":"Liu","sequence":"additional","affiliation":[{"name":"AI Research of JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Lei","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, college of computer science, Guizhou University, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5974-1570","authenticated-orcid":false,"given":"Youliang","family":"Tian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, college of computer science, Guizhou University, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A baseline for visual instance retrieval with deep convolutional networks","volume-title":"Proc. ICLR","author":"Ali","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00013"},{"key":"ref4","article-title":"Analyzing inverse problems with invertible neural networks","author":"Ardizzone","year":"2018"},{"key":"ref5","first-page":"1269","article-title":"Aggregating local deep features for image retrieval","volume-title":"Proc. ICCV","author":"Babenko","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02157"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18197-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.314"},{"key":"ref10","first-page":"17","article-title":"Deep learning of representations for unsupervised and transfer learning","volume-title":"Proc. ICML","author":"Bengio","year":"2012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3266418"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2019.0985"},{"key":"ref13","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2914897"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.598"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref24","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. ICML","author":"Chen","year":"2020"},{"key":"ref25","article-title":"Isolating sources of disentanglement in variational autoencoders","volume":"31","author":"Chen","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3218591"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531405"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref29","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021"},{"key":"ref30","first-page":"1251","article-title":"Xception: Deep learning with depthwise separable convolutions","volume-title":"Proc. CVPR","author":"Fran\u00e7","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-024-00294-7"},{"key":"ref33","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+","author":"Courbariaux","year":"2016"},{"key":"ref34","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume-title":"Proc. ECCV","volume":"1","author":"Csurka","year":"2004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref37","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"NIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3160658"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref42","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"Denton","year":"2014"},{"key":"ref43","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3149858"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2700390"},{"key":"ref46","article-title":"Repmlp: Re-parameterizing convolutions into fully-connected layers for image recognition","author":"Ding","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00527"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2891246"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100379"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108886"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-013-0336-8"},{"key":"ref52","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01518"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.513"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01064"},{"issue":"1","key":"ref57","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"JMLR"},{"key":"ref58","article-title":"Is attention better than matrix decomposition?","author":"Geng","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1561\/2200000089"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref62","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014"},{"key":"ref63","article-title":"On distinguishability criteria for estimating generative models","author":"Goodfellow","year":"2014"},{"key":"ref64","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/isbi53787.2023.10230838"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093311"},{"key":"ref69","article-title":"Knowledge distillation in vision transformers: A critical review","author":"Habib","year":"2023"},{"key":"ref70","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00599"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00737"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.68"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref79","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref84","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref85","first-page":"3304","article-title":"Aggregating local descriptors into a compact image representation","volume-title":"Proc. CVPR","author":"Herv\u00e9","year":"2010"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref87","article-title":"Combination of multiple global descriptors for image retrieval","author":"Jun","year":"2019"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3144651"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_45"},{"key":"ref90","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. NIPS","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298947"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/332"},{"key":"ref96","article-title":"Moganet: Multi-order gated aggregation network","volume-title":"Proc. ICLR","author":"Li","year":"2023"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01175"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.613"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2624140"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01331-0"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00085"},{"key":"ref105","first-page":"1992","article-title":"Transmatcher: Deep image matching through transformers for generalizable person re-identification","volume":"34","author":"Liao","year":"2021"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301269"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014440"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.227"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.090"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6834"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105373"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01170"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209999"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310333"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01206"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3302008"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"ref129","first-page":"327","article-title":"Bags of local convolutional features for scalable instance search","volume-title":"Proc. ICMR","year":"2016"},{"key":"ref130","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_16"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3054609"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref136","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proc. CVPR","volume":"\u2013660","author":"Qi","year":"2017"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"ref138","first-page":"12179","article-title":"Vision transformers for dense prediction","volume-title":"Proc. ICCV","author":"Ren\u00e9","year":"2021"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref140","article-title":"Faster r-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NIPS","volume":"28","author":"Ren","year":"2015"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054599"},{"key":"ref147","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013"},{"key":"ref148","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref150","article-title":"Sniper: Efficient multi-scale training","volume":"31","author":"Singh","year":"2018"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2848543"},{"key":"ref153","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref156","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan","year":"2019"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2816743"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.023"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01082"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref161","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICCV","author":"Touvron","year":"2021"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"issue":"66\u201371","key":"ref163","article-title":"Dimensionality reduction: A comparative","volume":"10","author":"Maaten","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref164","first-page":"5998","article-title":"Attention is all you need","year":"2017","journal-title":"NIPS"},{"key":"ref165","article-title":"Harnessing diffusion models for visual perception with meta prompts","author":"Wan","year":"2023"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2675339"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301333"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.081"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.03.010"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3266431"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.06.010"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004249"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109547"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.004"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01609"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212434"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.008"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2666739"},{"key":"ref184","article-title":"Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","author":"Wortsman","year":"2022"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00064"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.152"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8952"},{"key":"ref190","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Neural Inf. Process Syst."},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2511543"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2837381"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref194","first-page":"4203","article-title":"Focal modulation networks","volume":"35","author":"Yang","year":"2022"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.144"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2765830"},{"key":"ref197","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301272"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref204","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. ICCV","author":"Zhang","year":"2019"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw56347.2022.00309"},{"key":"ref206","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.06.008"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3124231"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3316180"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01374"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref215","article-title":"Object detectors emerge in deep scene CNNS","author":"Zhou","year":"2014"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref217","article-title":"Learning deep features for scene recognition using places database","volume-title":"Proc. NIPS","author":"Zhou","year":"2014"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10235"},{"key":"ref220","article-title":"Semi-supervised learning literature survey","author":"Zhu","year":"2005"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.641"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"ref225","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11021002\/10830500.pdf?arnumber=10830500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:01:08Z","timestamp":1764270068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10830500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":225,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3526138","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}