{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T16:48:06Z","timestamp":1745426886209,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"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":[[2024,6,17]]},"DOI":"10.1109\/cvprw63382.2024.00799","type":"proceedings-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:27:42Z","timestamp":1727461662000},"page":"8006-8015","source":"Crossref","is-referenced-by-count":2,"title":["ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration"],"prefix":"10.1109","author":[{"given":"Ning-Chi","family":"Huang","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University"}]},{"given":"Chi-Chih","family":"Chang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}]},{"given":"Wei-Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}]},{"given":"Endri","family":"Taka","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}]},{"given":"Diana","family":"Marculescu","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}]},{"given":"Kai-Chiang","family":"Wu","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Accelerating attention based models via HW-SW co-design using fine-grained sparsification","author":"Bambhaniya","year":"2023","journal-title":"Architecture and System Support for Transformer Models (ASSYST @ISCA 2023)"},{"article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Cai","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","first-page":"19974","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"Dosovitskiy","key":"ref5"},{"key":"ref6","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"International Conference on Machine Learning","author":"Evci"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2022.3197282"},{"article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022","author":"Frantar","key":"ref8"},{"key":"ref9","first-page":"544","article-title":"Single path oneshot neural architecture search with uniform sampling","author":"Guo","year":"2020","journal-title":"ECCV"},{"key":"ref10","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071058"},{"article-title":"Adam: A method for stochastic optimization","year":"2017","author":"Kingma","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"article-title":"CAP: correlation-aware pruning for highly-accurate sparse vision models","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023","author":"Kuznedelev","key":"ref15"},{"article-title":"Layer-adaptive sparsity for the magnitude-based pruning","year":"2020","author":"Lee","key":"ref16"},{"key":"ref17","article-title":"FQ-ViT: Fully quantized vision transformer without retraining","author":"Lin","year":"2021","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref19","first-page":"28092","article-title":"Post-training quantization for vision transformer","author":"Liu","year":"2021","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00049"},{"key":"ref21","first-page":"22812","article-title":"STEP: learning N: M structured sparsity masks from scratch with precondition","volume-title":"International Conference on Machine Learning, ICML 2023","author":"Lu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/3571419"},{"key":"ref23","article-title":"Are sixteen heads really better than one?","volume-title":"Advances in Neural Information Processing Systems","author":"Michel","year":"2019"},{"key":"ref24","article-title":"Accelerating sparse deep neural networks","author":"Mishra","year":"2021","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04316-3"},{"article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Molchanov","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"journal-title":"A100 tensor core gpu architecture","year":"2020","key":"ref28"},{"key":"ref29","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"2021","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Single-path NAS: designing hardware-efficient convnets in less than 4 hours","author":"Stamoulis","year":"2019","journal-title":"ECML PKDD"},{"key":"ref31","article-title":"Dominosearch: Find layer-wise fine-grained n:m sparse schemes from dense neural networks","author":"Sun","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","first-page":"10347","article-title":"Training data-efficient image transformers amp; distillation through attention","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Touvron"},{"key":"ref33","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"Wan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20222"},{"key":"ref35","article-title":"Unified visual transformer compression","author":"Yu","year":"2022","journal-title":"ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01183"},{"article-title":"Learning best combination for efficient N: M sparsity","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022","author":"Zhang","key":"ref37"},{"article-title":"Learning n: m fine-grained structured sparse neural networks from scratch","year":"2021","author":"Zhou","key":"ref38"},{"article-title":"Deformable {detr}: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations","author":"Zhu","key":"ref39"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","start":{"date-parts":[[2024,6,17]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2024,6,18]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10677511\/10677844\/10678399.pdf?arnumber=10678399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T04:06:34Z","timestamp":1727582794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10678399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,17]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/cvprw63382.2024.00799","relation":{},"subject":[],"published":{"date-parts":[[2024,6,17]]}}}