{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:28:17Z","timestamp":1750220897084,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T00:00:00Z","timestamp":1568764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,9,18]]},"DOI":"10.1145\/3366750.3366751","type":"proceedings-article","created":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T13:04:52Z","timestamp":1577106292000},"page":"3-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Using Distillation to Improve Network Performance after Pruning and Quantization"],"prefix":"10.1145","author":[{"given":"Zhenshan","family":"Bao","sequence":"first","affiliation":[{"name":"Beijing University of Technology, Beijing China"}]},{"given":"Jiayang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing China"}]},{"given":"Wenbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing China"}]}],"member":"320","published-online":{"date-parts":[[2019,9,18]]},"reference":[{"volume-title":"NIPS'89 Proceedings of the 2nd International Conference on Neural Information Processing Systems. 598--605","author":"LeCun Y.","key":"e_1_3_2_1_1_1","unstructured":"LeCun , Y. , Denker , J. S. , and Solla , S. A . 1990. Optimal brain damage . NIPS'89 Proceedings of the 2nd International Conference on Neural Information Processing Systems. 598--605 . LeCun, Y., Denker, J. S., and Solla, S. A. 1990. Optimal brain damage. NIPS'89 Proceedings of the 2nd International Conference on Neural Information Processing Systems. 598--605."},{"key":"e_1_3_2_1_2_1","unstructured":"Hassibi B. and Stork D. G. 1993. Second order derivatives for network pruning: Optimal brain surgeon. In Advances in neural information processing systems. 164--171.  Hassibi B. and Stork D. G. 1993. Second order derivatives for network pruning: Optimal brain surgeon. In Advances in neural information processing systems. 164--171."},{"key":"e_1_3_2_1_3_1","unstructured":"Han S. Pool J. Tran J. and Dally W. 2015. Learning both weights and connections for efficient neural network. In Advances in neural information processing systems. 1135--1143.  Han S. Pool J. Tran J. and Dally W. 2015. Learning both weights and connections for efficient neural network. In Advances in neural information processing systems. 1135--1143."},{"volume-title":"International Conference of Learning Representation. arXiv preprint arXiv:1611","author":"Molchanov P.","key":"e_1_3_2_1_4_1","unstructured":"Molchanov , P. , Tyree , S. , Karras , T. , Aila , T. , and Kautz , J . 2017. Pruning convolutional neural networks for resource efficient inference . In International Conference of Learning Representation. arXiv preprint arXiv:1611 .06440 Molchanov, P., Tyree, S., Karras, T., Aila, T., and Kautz, J. 2017. Pruning convolutional neural networks for resource efficient inference. In International Conference of Learning Representation. arXiv preprint arXiv:1611.06440"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"He Y. Liu P. Wang Z. and Yang Y. 2018. Pruning Filter via Geometric Median for Deep Convolutional Neural Networks Acceleration. arXiv preprint arXiv:1811.00250.  He Y. Liu P. Wang Z. and Yang Y. 2018. Pruning Filter via Geometric Median for Deep Convolutional Neural Networks Acceleration. arXiv preprint arXiv:1811.00250.","DOI":"10.1109\/CVPR.2019.00447"},{"key":"e_1_3_2_1_6_1","unstructured":"Singh P. Verma V. K. Rai P. and Namboodiri V. P. 2018. Leveraging Filter Correlations for Deep Model Compression. arXiv preprint arXiv:1811.10559.  Singh P. Verma V. K. Rai P. and Namboodiri V. P. 2018. Leveraging Filter Correlations for Deep Model Compression. arXiv preprint arXiv:1811.10559."},{"key":"e_1_3_2_1_7_1","unstructured":"Gong Y. Liu L. Yang M. and Bourdev L. 2014. Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115.  Gong Y. Liu L. Yang M. and Bourdev L. 2014. Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4820--4828","author":"Wu J.","key":"e_1_3_2_1_8_1","unstructured":"Wu , J. , Leng , C. , Wang , Y. , Hu , Q. , and Cheng , J . 2016. Quantized convolutional neural networks for mobile devices . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4820--4828 . Wu, J., Leng, C., Wang, Y., Hu, Q., and Cheng, J. 2016. Quantized convolutional neural networks for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4820--4828."},{"volume-title":"International Conference on Machine Learning. 1737--1746","author":"Gupta S.","key":"e_1_3_2_1_9_1","unstructured":"Gupta , S. , Agrawal , A. , Gopalakrishnan , K. , and Narayanan , P . 2015. Deep learning with limited numerical precision . In International Conference on Machine Learning. 1737--1746 . Gupta, S., Agrawal, A., Gopalakrishnan, K., and Narayanan, P. 2015. Deep learning with limited numerical precision. In International Conference on Machine Learning. 1737--1746."},{"key":"e_1_3_2_1_10_1","volume-title":"Ristretto: Hardware-oriented approximation of convolutional neural networks. arXiv preprint arXiv:1605.06402","author":"Gysel P.","year":"2016","unstructured":"Gysel , P. , Motamedi , M. , and Ghiasi , S . 2016 . Ristretto: Hardware-oriented approximation of convolutional neural networks. arXiv preprint arXiv:1605.06402 Gysel, P., Motamedi, M., and Ghiasi, S. 2016. Ristretto: Hardware-oriented approximation of convolutional neural networks. arXiv preprint arXiv:1605.06402"},{"key":"e_1_3_2_1_11_1","unstructured":"Courbariaux M. Hubara I. Soudry D. El-Yaniv R. and Bengio Y. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or -1. arXiv preprint arXiv:1602.02830.  Courbariaux M. Hubara I. Soudry D. El-Yaniv R. and Bengio Y. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or -1. arXiv preprint arXiv:1602.02830."},{"key":"e_1_3_2_1_12_1","unstructured":"Li F. Zhang B. and Liu B. 2016. Ternary weight networks. arXiv preprint arXiv:1605.04711.  Li F. Zhang B. and Liu B. 2016. Ternary weight networks. arXiv preprint arXiv:1605.04711."},{"key":"e_1_3_2_1_13_1","unstructured":"Hinton G. Vinyals O. and Dean J. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.  Hinton G. Vinyals O. and Dean J. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531."},{"key":"e_1_3_2_1_14_1","volume-title":"Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550.","author":"Romero A.","year":"2014","unstructured":"Romero , A. , Ballas , N. , Kahou , S. E. , Chassang , A. , Gatta , C. , and Bengio , Y . 2014 . Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550. Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., and Bengio, Y. 2014. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4133--4141","author":"Yim J.","key":"e_1_3_2_1_15_1","unstructured":"Yim , J. , Joo , D. , Bae , J. , and Kim , J . 2017. A gift from knowledge distillation: Fast optimization, network minimization and transfer learning . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4133--4141 . Yim, J., Joo, D., Bae, J., and Kim, J. 2017. A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4133--4141."},{"volume-title":"International Conference of Learning Representation.","author":"Mishra A.","key":"e_1_3_2_1_16_1","unstructured":"Mishra , A. , and Marr , D . 2018. Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy . In International Conference of Learning Representation. Mishra, A., and Marr, D. 2018. Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy. In International Conference of Learning Representation."},{"key":"e_1_3_2_1_17_1","unstructured":"Han S. Mao H. and Dally W. J. 2015. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. arXiv preprint arXiv:1510.00149.  Han S. Mao H. and Dally W. J. 2015. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. arXiv preprint arXiv:1510.00149."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Oguntola I. Olubeko S. and Sweeney C. 2018. SlimNets: An Exploration of Deep Model Compression and Acceleration. In 2018 IEEE High Performance extreme Computing Conference.1--6.  Oguntola I. Olubeko S. and Sweeney C. 2018. SlimNets: An Exploration of Deep Model Compression and Acceleration. In 2018 IEEE High Performance extreme Computing Conference.1--6.","DOI":"10.1109\/HPEC.2018.8547604"},{"key":"e_1_3_2_1_19_1","unstructured":"Polino A. Pascanu R. and Alistarh D.2018. Model compression via distillation and quantization. arXiv preprint arXiv:1802.05668  Polino A. Pascanu R. and Alistarh D.2018. Model compression via distillation and quantization. arXiv preprint arXiv:1802.05668"}],"event":{"name":"MLMI 2019: 2019 2nd International Conference on Machine Learning and Machine Intelligence","acronym":"MLMI 2019","location":"Jakarta Indonesia"},"container-title":["Proceedings of the 2019 2nd International Conference on Machine Learning and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366750.3366751","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3366750.3366751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:39Z","timestamp":1750203879000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366750.3366751"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,18]]},"references-count":19,"alternative-id":["10.1145\/3366750.3366751","10.1145\/3366750"],"URL":"https:\/\/doi.org\/10.1145\/3366750.3366751","relation":{},"subject":[],"published":{"date-parts":[[2019,9,18]]},"assertion":[{"value":"2019-09-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}