{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:54:19Z","timestamp":1775325259662,"version":"3.50.1"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/hpca56546.2023.10071047","type":"proceedings-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T17:42:55Z","timestamp":1679679775000},"page":"442-455","source":"Crossref","is-referenced-by-count":93,"title":["HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers"],"prefix":"10.1109","author":[{"given":"Peiyan","family":"Dong","sequence":"first","affiliation":[{"name":"Northeastern University"}]},{"given":"Mengshu","family":"Sun","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Alec","family":"Lu","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}]},{"given":"Yanyue","family":"Xie","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Kenneth","family":"Liu","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}]},{"given":"Zhenglun","family":"Kong","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Xin","family":"Meng","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Zhengang","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Zhenman","family":"Fang","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University"}]}],"member":"263","reference":[{"key":"ref1","author":"Agarap","year":"2018","journal-title":"Deep learning using rectified linear units (relu)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref9","first-page":"8714","article-title":"Searching the search space of vision transformer","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref10","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref12","volume-title":"Torchvision","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT47387.2019.00009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT47387.2019.00009"},{"key":"ref16","article-title":"Nasvit: Neural architecture search for efficient vision transformers with gradient conflict aware supernet training","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gong"},{"key":"ref17","volume-title":"Deep Learning.","author":"Goodfellow","year":"2016"},{"key":"ref18","article-title":"Nat: Neural architecture transformer for accurate and compact architectures","volume":"32","author":"Guo","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref19","article-title":"Transformer in transformer","author":"Han","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","author":"Hendrycks","year":"2016","journal-title":"Gaussian error linear units (gelus)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref25","author":"Jiang","year":"2021","journal-title":"All tokens matter: Token labeling for training better vision transformers"},{"key":"ref26","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton"},{"key":"ref27","author":"Kim","year":"2021","journal-title":"I-bert: Integer-only bert quantization"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref29","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"International Conference on Machine Learning (ICML)","author":"Kornblith"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00027"},{"key":"ref33","article-title":"EVit: Expediting vision transformers via token reorganizations","volume-title":"International Conference on Learning Representations","author":"Liang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref35","first-page":"092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref36","article-title":"Dual-stream network for visual recognition","author":"Mao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/319382.319388"},{"key":"ref38","article-title":"Ia-red2: Interpretability-aware redundancy reduction for vision transformers","author":"Pan","year":"2021","journal-title":"in Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461739"},{"key":"ref42","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","first-page":"5877","article-title":"The evolved transformer","volume-title":"International Conference on Machine Learning (ICML)","author":"So"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502364"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01185"},{"key":"ref46","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CADSM.2019.8779253"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref52","volume-title":"Vitis unified software platform","year":"2022"},{"key":"ref53","volume-title":"Zcu102 evaluation board - user guide","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3646-6"},{"key":"ref57","article-title":"Unified visual transformer compression","volume-title":"International Conference on Learning Representations","author":"Yu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2785257"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3477002"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_29"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref63","author":"Zhou","year":"2021","journal-title":"Refiner: Refining self-attention for vision transformers"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref65","article-title":"Visual transformer pruning","volume-title":"KDD 2021 Workshop on Model Mining","author":"Zhu"},{"key":"ref66","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhu"}],"event":{"name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2023,2,25]]},"end":{"date-parts":[[2023,3,1]]}},"container-title":["2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10070856\/10070923\/10071047.pdf?arnumber=10071047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T06:34:27Z","timestamp":1709447667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10071047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/hpca56546.2023.10071047","relation":{},"subject":[],"published":{"date-parts":[[2023,2]]}}}