{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:01:04Z","timestamp":1777654864748,"version":"3.51.4"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014188","name":"MSIT","doi-asserted-by":"publisher","award":["2022R1C1C1008131,2022R1C1C1011307"],"award-info":[{"award-number":["2022R1C1C1008131,2022R1C1C1011307"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.00813","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"8301-8311","source":"Crossref","is-referenced-by-count":29,"title":["It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher"],"prefix":"10.1109","author":[{"given":"Kanghyun","family":"Choi","sequence":"first","affiliation":[{"name":"College of Computing, Yonsei University"}]},{"given":"Hye Yoon","family":"Lee","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}]},{"given":"Deokki","family":"Hong","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}]},{"given":"Joonsang","family":"Yu","sequence":"additional","affiliation":[{"name":"CLOVA ImageVision,CLOVA AI Lab, NAVER"}]},{"given":"Noseong","family":"Park","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}]},{"given":"Youngsok","family":"Kim","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}]},{"given":"Jinho","family":"Lee","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/478"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00156"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00121"},{"key":"ref33","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref32","first-page":"6","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref31","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"shirish keskar","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref37","article-title":"Fixed point quantization of deep convolutional networks","author":"lin","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref36","article-title":"Invertible tabular GANs: Killing two birds with one stone for tabular data synthesis","author":"lee","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref35","author":"lanczos","year":"1950","journal-title":"An Iteration Method for the Solution of the Eigenvalue Problem of Linear Differential and Integral Operators"},{"key":"ref34","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref60","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref62","first-page":"1","article-title":"Generative low-bitwidth data free quantization","author":"xu","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00400"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378171"},{"key":"ref28","article-title":"The break-even point on optimization trajectories of deep neural networks","author":"jastrzebski","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref64","article-title":"Dreaming to distill: Data-free knowledge transfer via deep-inversion","author":"yin","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref27","article-title":"On the relation between the sharpest directions of dnn loss and the sgd step length","author":"jastrzebski","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref65","article-title":"Large batch training of convolutional networks","author":"you","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref66","article-title":"LQ-Nets: Learned quantization for highly accurate and compact deep neural networks","author":"zhang","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01540"},{"key":"ref68","first-page":"1","article-title":"Improving neural network quantization without retraining using outlier channel splitting","author":"zhao","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref69","first-page":"1","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Critical learning periods in deep neural networks","author":"achille","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref1","year":"0","journal-title":"Computer vision models on PyTorch"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00852"},{"key":"ref22","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Advances in Neural Information Processing Systems Workshops"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref23","article-title":"Fixed-point feedforward deep neural network design using weights+ 1,0, and-1","author":"hwang","year":"2014","journal-title":"Workshop on Signal Processing Systems"},{"key":"ref26","article-title":"Three factors influencing minima in SGD","author":"jastrzebski","year":"2018","journal-title":"Int Conf Artificial Neural Networks"},{"key":"ref25","article-title":"Catastrophic fisher explosion: Early phase fisher matrix impacts generalization","author":"jastrzebski","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231757"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5220\/0010246602590267"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref56","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref55","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref53","first-page":"1","article-title":"XNOR-Net: Imagenet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref52","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Advances in Neural Information Processing Systems Workshops"},{"key":"ref10","first-page":"1","article-title":"Qimera: Data-free quantization with synthetic boundary supporting samples","author":"choi","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00363"},{"key":"ref40","article-title":"Bi-Real net: Enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm","author":"liu","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"ref12","article-title":"Towards the limit of network quantization","author":"choi","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00393"},{"key":"ref14","first-page":"1","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.522"},{"key":"ref16","article-title":"Adapting auxiliary losses using gradient similarity","author":"du","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00452"},{"key":"ref18","author":"forouzesh","year":"2020","journal-title":"Early stopping by gradient disparity"},{"key":"ref19","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref4","first-page":"1","article-title":"Post-training 4-bit quantization of convolution networks for rapid-deployment","author":"banner","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"guo","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"ref8","first-page":"1","article-title":"On the efficacy of knowledge distillation","author":"hyun cho","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref7","article-title":"Entropy-SGD: Biasing gradient descent into wide valleys","author":"chaudhari","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.29007\/shbv"},{"key":"ref46","article-title":"Loss aware post-training quantization","author":"nahshan","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref48","article-title":"Conditional image synthesis with auxiliary classifier GANs","author":"odena","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref47","article-title":"A method for solving the convex programming problem with convergence rate O(1\/k2)","author":"evgen'evich nesterov","year":"1983","journal-title":"Dokl Akad Nauk SSSR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref44","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"Advances in Neural Information Processing Systems Workshops"},{"key":"ref43","article-title":"Early stopping without a validation set","author":"mahsereci","year":"2017","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"New Orleans, LA, USA","start":{"date-parts":[[2022,6,18]]},"end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09878460.pdf?arnumber=9878460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:58:56Z","timestamp":1665781136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9878460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.00813","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}