{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:07Z","timestamp":1750309507707,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3656256","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LEAF: An Adaptation Framework against Noisy Data on Edge through Ultra Low-Cost Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8720-8618","authenticated-orcid":false,"given":"Zihan","family":"Xia","sequence":"first","affiliation":[{"name":"University of California San Diego, La Jolla, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8716-5877","authenticated-orcid":false,"given":"Jinwook","family":"Kim","sequence":"additional","affiliation":[{"name":"Sk Hynix inc., Icheon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8104-5136","authenticated-orcid":false,"given":"Mingu","family":"Kang","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, CA, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085","author":"Jungwook Choi","year":"2018","unstructured":"Jungwook Choi et al. Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085, 2018."},{"key":"e_1_3_2_1_2_1","first-page":"1","volume-title":"DAC","author":"Seungkyu","year":"2019","unstructured":"Seungkyu Choi et al. An optimized design technique of low-bit neural network training for personalization on iot devices. In DAC, pages 1--6, 2019."},{"issue":"5","key":"e_1_3_2_1_3_1","first-page":"1574","article-title":"Accelerating on-device dnn training workloads via runtime convergence monitor","volume":"42","author":"Seungkyu Choi","year":"2023","unstructured":"Seungkyu Choi et al. Accelerating on-device dnn training workloads via runtime convergence monitor. IEEE TCAD, 42(5):1574--1587, 2023.","journal-title":"IEEE TCAD"},{"key":"e_1_3_2_1_4_1","first-page":"12043","volume-title":"A salt and pepper noise image denoising method based on the generative classification. Multimedia tools and applications","author":"Bo Fu","year":"2019","unstructured":"Bo Fu et al. A salt and pepper noise image denoising method based on the generative classification. Multimedia tools and applications, pages 12043--12053, 2019."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_6_1","volume-title":"Learning multiple layers of features from tiny images","author":"Alex Krizhevsky","year":"2009","unstructured":"Alex Krizhevsky et al. Learning multiple layers of features from tiny images. 2009."},{"issue":"7","key":"e_1_3_2_1_7_1","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Ya Le","year":"2015","unstructured":"Ya Le et al. Tiny imagenet visual recognition challenge. CS 231N, 7(7):3, 2015.","journal-title":"CS 231N"},{"key":"e_1_3_2_1_8_1","first-page":"115","volume-title":"IEEE OJ-SSCS","author":"Jinsu","year":"2021","unstructured":"Jinsu Lee et al. An overview of energy-efficient hardware accelerators for on-device deep-neural-network training. IEEE OJ-SSCS, pages 115--128, 2021."},{"key":"e_1_3_2_1_9_1","first-page":"6448","volume-title":"CVPR","author":"Junghyup","year":"2021","unstructured":"Junghyup Lee et al. Network quantization with element-wise gradient scaling. In CVPR, pages 6448--6457, 2021."},{"key":"e_1_3_2_1_10_1","first-page":"182","volume-title":"IEEE JSSC","author":"Kyu Sae","year":"2022","unstructured":"Sae Kyu Lee et al. A 7-nm four-core mixed-precision ai chip with 26.2-tflops hybrid-fp8 training, 104.9-tops int4 inference, and workload-aware throttling. IEEE JSSC, pages 182--197, 2022."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00338"},{"key":"e_1_3_2_1_12_1","first-page":"1118","volume-title":"ICIP","author":"Mading","year":"2018","unstructured":"Mading Li et al. Restoration of unevenly illuminated images. In ICIP, pages 1118--1122, 2018."},{"key":"e_1_3_2_1_13_1","first-page":"22941","volume-title":"Advances in Neural Information Processing Systems","author":"Ji","year":"2022","unstructured":"Ji Lin et al. On-device training under 256kb memory. In Advances in Neural Information Processing Systems, pages 22941--22954. Curran Associates, Inc., 2022."},{"key":"e_1_3_2_1_14_1","first-page":"1","volume-title":"2020 IEEE Symposium on VLSI Circuits","author":"Jinwook","year":"2020","unstructured":"Jinwook Oh et al. A 3.0 tflops 0.62v scalable processor core for high compute utilization ai training and inference. In 2020 IEEE Symposium on VLSI Circuits, pages 1--2, 2020."},{"key":"e_1_3_2_1_15_1","article-title":"Effects of image degradation and degradation removal to cnn-based image classification","author":"Yanting Pei","year":"2021","unstructured":"Yanting Pei et al. Effects of image degradation and degradation removal to cnn-based image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1239--1253, 2021.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1239--1253"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1964.1088973"},{"key":"e_1_3_2_1_17_1","first-page":"1","volume-title":"DAC","author":"Dongyeob","year":"2020","unstructured":"Dongyeob Shin et al. Prediction confidence based low complexity gradient computation for accelerating dnn training. In DAC, pages 1--6, 2020."},{"key":"e_1_3_2_1_18_1","volume-title":"IEEE TNNLS","author":"Dongyeob","year":"2023","unstructured":"Dongyeob Shin et al. Low complexity gradient computation techniques to accelerate deep neural network training. IEEE TNNLS, 2023."},{"key":"e_1_3_2_1_19_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Karen Simonyan","year":"2014","unstructured":"Karen Simonyan et al. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_20_1","volume-title":"Journal of Semiconductors","author":"Chunyou","year":"2020","unstructured":"Chunyou Su et al. Towards high performance low bitwidth training for deep neural networks. Journal of Semiconductors, 2020."},{"key":"e_1_3_2_1_21_1","first-page":"769","volume-title":"CVPR","author":"Jian","year":"2015","unstructured":"Jian Sun et al. Learning a convolutional neural network for non-uniform motion blur removal. In CVPR, pages 769--777, 2015."},{"key":"e_1_3_2_1_22_1","first-page":"1796","volume-title":"NeurIPS","author":"Xiao","year":"2020","unstructured":"Xiao Sun et al. Ultra-low precision 4-bit training of deep neural networks. In NeurIPS, pages 1796--1807, 2020."},{"key":"e_1_3_2_1_23_1","volume-title":"Gradient distribution-aware int8 training for neural networks. Neurocomput., jul","author":"Shuai Wang","year":"2023","unstructured":"Shuai Wang et al. Gradient distribution-aware int8 training for neural networks. Neurocomput., jul 2023."},{"key":"e_1_3_2_1_24_1","volume-title":"H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc","author":"Yue Wang","year":"2019","unstructured":"Yue Wang et al. E2-train: Training state-of-the-art cnns with over 80% energy savings. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett, editors, NeurIPS, volume 32. Curran Associates, Inc., 2019."},{"key":"e_1_3_2_1_25_1","first-page":"3096","volume-title":"CVPRW","author":"Simon","year":"2020","unstructured":"Simon Wiedemann et al. Dithered backprop: A sparse and quantized backprop-agation algorithm for more efficient deep neural network training. In CVPRW, pages 3096--3104, 2020."},{"key":"e_1_3_2_1_26_1","first-page":"70","volume-title":"Neural Networks","author":"Yukuan","year":"2020","unstructured":"Yukuan Yang et al. Training high-performance and large-scale deep neural networks with full 8-bit integers. Neural Networks, pages 70--82, 2020."},{"key":"e_1_3_2_1_27_1","first-page":"34","volume-title":"ECCV","author":"Geng","year":"2022","unstructured":"Geng Yuan et al. You already have it: A generator-free low-precision dnn training framework using stochastic rounding. In ECCV, pages 34--51. Springer, 2022."},{"key":"e_1_3_2_1_28_1","first-page":"3483","volume-title":"AAAI","author":"Kang","year":"2021","unstructured":"Kang Zhao et al. Distribution adaptive int8 quantization for training cnns. In AAAI, pages 3483--3491, 2021."},{"key":"e_1_3_2_1_29_1","volume-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160","author":"Shuchang Zhou","year":"2016","unstructured":"Shuchang Zhou et al. Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160, 2016."},{"key":"e_1_3_2_1_30_1","first-page":"1213","volume-title":"ICASSP","author":"Yiren","year":"2017","unstructured":"Yiren Zhou et al. On classification of distorted images with deep convolutional neural networks. In ICASSP, pages 1213--1217, 2017."},{"key":"e_1_3_2_1_31_1","first-page":"1966","volume-title":"CVPR","author":"Feng","year":"2020","unstructured":"Feng Zhu et al. Towards unified int8 training for convolutional neural network. In CVPR, pages 1966--1976, 2020."}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"San Francisco CA USA","acronym":"DAC '24"},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656256","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3656256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":31,"alternative-id":["10.1145\/3649329.3656256","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3656256","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}