{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:17:39Z","timestamp":1730225859123,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency (DARPA)","doi-asserted-by":"publisher","award":["HR00111890042"],"award-info":[{"award-number":["HR00111890042"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1640012"],"award-info":[{"award-number":["CCF-1640012"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","award":["2016-EP-2693-B"],"award-info":[{"award-number":["2016-EP-2693-B"]}],"id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,25]]},"DOI":"10.1109\/hpec58863.2023.10363613","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:39:57Z","timestamp":1703533197000},"page":"1-12","source":"Crossref","is-referenced-by-count":0,"title":["Asymmetric Grouped Convolutions for Logarithmic Scale Efficient Convolutional Neural Networks"],"prefix":"10.1109","author":[{"given":"Li","family":"Jing","sequence":"first","affiliation":[{"name":"MIT Physics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rumen","family":"Dangovski","sequence":"additional","affiliation":[{"name":"MIT EECS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marin","family":"Solja\u010di\u0107","sequence":"additional","affiliation":[{"name":"MIT Physics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Long-former: The long-document transformer","year":"2020","author":"Beltagy","key":"ref1"},{"journal-title":"Generating long sequences with sparse transformers","year":"2019","author":"Child","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.195"},{"key":"ref4","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref5"},{"article-title":"Nasvit: Neural architecture search for efficient vision transformers with gradient conflict aware supernet training","volume-title":"International Conference on Learning Representations","author":"Gong","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref12","article-title":"Squeezenet: Alexnet-Ievel accuracy with 50x fewer parameters and 0.5 MB model size","author":"Iandola","year":"2016","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.633"},{"key":"ref14","article-title":"Waveletnet: Logarithmic scale efficient convolutional neural networks for edge devices","author":"Jing","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/45.666645"},{"issue":"7","key":"ref16","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"Krizhevsky","year":"2009","journal-title":"Technical report, University of Toronto"},{"key":"ref17","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Advances in neural information processing systems, NeurIPS 16","author":"Krizhevsky","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73603-7_10"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref20","first-page":"11976","article-title":"A con-vnet for the 2020s","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Liu","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref22","article-title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv preprint"},{"journal-title":"Separable self- attention for mobile vision transformers","year":"2022","author":"Mehta","key":"ref23"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1090\/stml\/063\/09","article-title":"Harmonic Analysis. From Frourier to Wavelets","volume":"63","author":"Cristina Pereyra","year":"2012","journal-title":"Student Mathe-matical Library, lAS\/Park City Mathematical Subseries"},{"key":"ref25","article-title":"Efficient neural architecture search via parameter sharing","author":"Pham","year":"2018","journal-title":"ICML"},{"key":"ref26","first-page":"2449","article-title":"Spec-tral representations for convolutional neural networks","author":"Rippel","year":"2015","journal-title":"Advances in neural information processing systems, NeurIPS 15"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"journal-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref29"},{"article-title":"IGCV3: interleaved low-rank group convolutions for ef-ficient deep neural networks","volume-title":"British Machine Vision Conference, BMVC 18","author":"Sun","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref35","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on ma-chine learning","author":"Touvron"},{"key":"ref37","volume":"30","author":"Vaswani","year":"2017","journal-title":"Attention is all you need. Advances in neural information processing systems"},{"key":"ref38","first-page":"545","article-title":"Fac-torized convolutional neural networks","volume-title":"International Conference on Computer Vision Workshops, ICCVW 17","author":"Wang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00922"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00922"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref42","article-title":"Dynamic mobile-former: Strengthening dynamic convolution with attention and residual connection in kernel space","author":"Yun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.469"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/440"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"event":{"name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2023,9,25]]},"location":"Boston, MA, USA","end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10363430\/10363422\/10363613.pdf?arnumber=10363613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T21:12:26Z","timestamp":1705093946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10363613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,25]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/hpec58863.2023.10363613","relation":{},"subject":[],"published":{"date-parts":[[2023,9,25]]}}}