{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:58:48Z","timestamp":1730303928256,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"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":[[2024,1,3]]},"DOI":"10.1109\/wacv57701.2024.00233","type":"proceedings-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T17:36:09Z","timestamp":1712684169000},"page":"2325-2334","source":"Crossref","is-referenced-by-count":0,"title":["Partial Binarization of Neural Networks for Budget-Aware Efficient Learning"],"prefix":"10.1109","author":[{"given":"Udbhav","family":"Bamba","sequence":"first","affiliation":[{"name":"Transmute AI Lab,India"}]},{"given":"Neeraj","family":"Anand","sequence":"additional","affiliation":[{"name":"Nyun AI,India"}]},{"given":"Saksham","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Transmute AI Lab,India"}]},{"given":"Dilip K.","family":"Prasad","sequence":"additional","affiliation":[{"name":"UiT The Arctic University of Norway,Norway"}]},{"given":"Deepak K.","family":"Gupta","sequence":"additional","affiliation":[{"name":"Transmute AI Lab,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.08342"},{"article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1","year":"2016","author":"Courbariaux","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Courbariaux","key":"ref7"},{"key":"ref8","article-title":"Towards accurate binary convolutional neural network","author":"Lin","year":"2017","journal-title":"ArXiv"},{"key":"ref9","article-title":"Training binary neural networks with real-to-binary convolutions","author":"Mart\u00ednez","year":"2020","journal-title":"ArXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01227-8"},{"article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","year":"2019","author":"Frankle","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size","author":"Iandola","year":"2016","journal-title":"ArXiv"},{"key":"ref14","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"ArXiv"},{"key":"ref15","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2017","journal-title":"ArXiv"},{"article-title":"Efficient neural architecture search via parameter sharing","volume-title":"International Conference on Machine Learning (ICML)","author":"Pham","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"journal-title":"Do deep convolutional nets really need to be deep and convolutional?","year":"2017","author":"Urban","key":"ref18"},{"article-title":"Do deep nets really need to be deep?","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ba","key":"ref19"},{"key":"ref20","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2015","journal-title":"CoRR"},{"journal-title":"Contrastive representation distillation","year":"2020","author":"Tian","key":"ref21"},{"journal-title":"Pruning filters for efficient convnets","year":"2017","author":"Li","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Dong","key":"ref24"},{"journal-title":"Snip: Single-shot network pruning based on connection sensitivity","year":"2019","author":"Lee","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00932"},{"article-title":"Chipnet: Budget-aware pruning with heaviside continuous approximations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tiwari","key":"ref27"},{"article-title":"Snip: Single-shot network pruning based on connection sensitivity","year":"2018","author":"Lee","key":"ref28"},{"key":"ref29","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume":"33","author":"Tanaka","year":"2020","journal-title":"Advances in neural information processing systems"},{"journal-title":"Aciq: Analytical clipping for integer quantization of neural networks","year":"2018","author":"Banner","key":"ref30"},{"article-title":"Linear symmetric quantization of neural networks for low-precision integer hardware","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhao","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16306"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6624"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00916"},{"key":"ref39","first-page":"18518","article-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Dong","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"}],"event":{"name":"2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","start":{"date-parts":[[2024,1,3]]},"location":"Waikoloa, HI, USA","end":{"date-parts":[[2024,1,8]]}},"container-title":["2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10483279\/10483282\/10483283.pdf?arnumber=10483283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T05:42:52Z","timestamp":1712727772000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10483283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/wacv57701.2024.00233","relation":{},"subject":[],"published":{"date-parts":[[2024,1,3]]}}}