{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:08:32Z","timestamp":1777889312954,"version":"3.51.4"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62322113,62376156"],"award-info":[{"award-number":["62322113,62376156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02159","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23256-23266","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Architecture Distillation Made Simple with Redundancy Suppression"],"prefix":"10.1109","author":[{"given":"Weijia","family":"Zhang","sequence":"first","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}]},{"given":"Yuehao","family":"Liu","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}]},{"given":"Wu","family":"Ran","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.3.308"},{"key":"ref2","article-title":"Vicreg: Variance-invariance-covariance regularization for selfsupervised learning","author":"Bardes","year":"2022","journal-title":"ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.3.295"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01163"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01174"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00377"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00110-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2022"},{"issue":"59","key":"ref16","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"JMLR"},{"key":"ref17","article-title":"On the duality between contrastive and non-contrastive self-supervised learning","author":"Garrido","year":"2023","journal-title":"ICLR"},{"key":"ref18","article-title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2018","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01142"},{"key":"ref21","article-title":"Learning efficient vision transformers via fine-grained manifold distillation","author":"Hao","year":"2022","journal-title":"NeurIPS"},{"key":"ref22","article-title":"One-for-all: Bridge the gap between heterogeneous architectures in knowledge distillation","author":"Hao","year":"2024","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref25","article-title":"Distilling the knowlegde in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv:1503.02531"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2443"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01818"},{"key":"ref28","article-title":"Similarity of neural network representations revisited","author":"Kornblith","year":"2019","journal-title":"ICML"},{"key":"ref29","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","journal-title":"2009. 6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00596"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"ref34","article-title":"Function-consistent feature distillation","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00816"},{"key":"ref36","article-title":"Cross-architecture knowledge distillation","author":"Liu","year":"2022","journal-title":"ACCV"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref39","article-title":"Domain-invariant feature exploration for domain generalization","author":"Lu","year":"2022","journal-title":"TMLR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref41","article-title":"Domain generalization via invariant feature representation","author":"Muandet","year":"2013","journal-title":"ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_18"},{"key":"ref43","article-title":"How do vision transformers work?","author":"Park","year":"2022","journal-title":"ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref46","article-title":"Efficient domain generalization via common-specific low-rank decomposition","author":"Piratla","year":"2020","journal-title":"ICML"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093795"},{"key":"ref48","article-title":"Do vision transformers see like convolutional neural networks? NeurIPS, 2021","author":"Raghu","journal-title":"1, 4"},{"key":"ref49","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2015","journal-title":"ICLR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"ref53","article-title":"Contrastive representation distillation","author":"Tian","year":"2020","journal-title":"I C L R"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref55","article-title":"The information bottleneck method","author":"Tishby","year":"2000","journal-title":"arXiv preprint physics\/0004057"},{"key":"ref56","article-title":"Mlp-mixer: An all-mlp architecture for vision","author":"Ilya","year":"2021","journal-title":"NeurIPS"},{"key":"ref57","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021","journal-title":"ICML"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref60","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref61","article-title":"Diffuse and disperse: Image generation with representation regularization","author":"Wang","year":"2025","journal-title":"arXiv:2506.09027"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref63","article-title":"Glance and focus: a dynamic approach to reducing spatial redundancy in image classification","author":"Wang","year":"2020","journal-title":"NeurIPS"},{"key":"ref64","article-title":"Improving knowledge distillation via regularizing feature norm and direction","author":"Wang","year":"2024","journal-title":"ECCV"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01512"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00039"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01576"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00145"},{"key":"ref72","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021","journal-title":"ICML"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02101"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681206"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00737"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00260"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref79","article-title":"Knowledge distillation based on transformed teaching matching","author":"Zheng","year":"2024","journal-title":"ICLR"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00495"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446081.pdf?arnumber=11446081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:15Z","timestamp":1777612155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02159","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}