{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:46:20Z","timestamp":1767725180217,"version":"3.48.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660101"],"award-info":[{"award-number":["XDB0660101"]}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660000"],"award-info":[{"award-number":["XDB0660000"]}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660100"],"award-info":[{"award-number":["XDB0660100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172380"],"award-info":[{"award-number":["62172380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241818"],"award-info":[{"award-number":["BK20241818"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"USTC Research Funds of the Double First-Class Initiative","award":["YD2150002011"],"award-info":[{"award-number":["YD2150002011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tai.2025.3576087","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T13:59:38Z","timestamp":1749045578000},"page":"439-454","source":"Crossref","is-referenced-by-count":0,"title":["FG-KD: A Novel Forward Gradient-Based Framework for Teacher Knowledge Augmentation"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1063-7182","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-5575","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8391-5526","authenticated-orcid":false,"given":"Lei","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R) and Centre for Frontier AI Research (CFAR), A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1719-0328","authenticated-orcid":false,"given":"Zhenghua","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R) and Centre for Frontier AI Research (CFAR), A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-3143","authenticated-orcid":false,"given":"Xuehai","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"article-title":"Fitnets: Hints for thin deep nets","year":"2014","author":"Romero","key":"ref3"},{"article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","year":"2016","author":"Zagoruyko","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref6","first-page":"13292","article-title":"Learning student-friendly teacher networks for knowledge distillation","volume":"34","author":"Park","year":"2021","journal-title":"Adv. Neur. Inf. Process. Syst."},{"key":"ref7","first-page":"9422","article-title":"Learning diverse and discriminative representations via the principle of maximal coding rate reduction","volume":"33","author":"Yu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"Redunet: A white-box deep network from the principle of maximizing rate reduction","year":"2021","author":"Chan","key":"ref8"},{"article-title":"Gradients Without Backpropagation","year":"2022","author":"Baydin","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref14"},{"key":"ref15","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Adv. Neur. Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01576"},{"key":"ref19","article-title":"Minillm: Knowledge distillation of large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Gu","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref23","first-page":"1","article-title":"One-for-all: Bridge the gap between heterogeneous architectures in knowledge distillation","volume":"36","author":"Hao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28219"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00914"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01515"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00574"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3354928"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00575"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref33","first-page":"13456","article-title":"What makes a \u201cgood\u201d data augmentation in knowledge distillation\u2014A statistical perspective","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref35","first-page":"134","article-title":"Spike-based learning rules and stabilization of persistent neural activity","volume":"12","author":"Xie","year":"1999","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(03)00761-X"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"article-title":"Learning deep representations by mutual information estimation and maximization","year":"2018","author":"Hjelm","key":"ref38"},{"article-title":"A rate-distortion framework for explaining neural network decisions","year":"2019","author":"MacDonald","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3343717"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref42"},{"key":"ref43","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume":"32","author":"Cao","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"Benchmarking neural network robustness to common corruptions and perturbations","year":"2019","author":"Hendrycks","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01489"},{"article-title":"Contrastive Representation Distillation","year":"2019","author":"Tian","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3141255"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref58","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"23","author":"Ren","year":"2015","journal-title":"Advances Neural Inf. Process. Syst."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref60","first-page":"237","article-title":"Augmax: Adversarial composition of random augmentations for robust training","volume":"34","author":"Wang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11329125\/11023585.pdf?arnumber=11023585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:38:43Z","timestamp":1767724723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11023585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":60,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3576087","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}