{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T21:50:57Z","timestamp":1755035457885,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,5]],"date-time":"2020-08-05T00:00:00Z","timestamp":1596585600000},"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":[[2020,8,5]]},"DOI":"10.1145\/3421558.3421559","type":"proceedings-article","created":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T20:31:31Z","timestamp":1606422691000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Stochastic Model Pruning via Weight Dropping Away and Back"],"prefix":"10.1145","author":[{"given":"Haipeng","family":"Jia","sequence":"first","affiliation":[{"name":"Qian Xuesen Laboratory of Space Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueshuang","family":"Xiang","sequence":"additional","affiliation":[{"name":"Qian Xuesen Laboratory of Space Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Fan","sequence":"additional","affiliation":[{"name":"Qian Xuesen Laboratory of Space Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiyu","family":"Huang","sequence":"additional","affiliation":[{"name":"Qian Xuesen Laboratory of Space Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhao","family":"Sun","sequence":"additional","affiliation":[{"name":"Qian Xuesen Laboratory of Space Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"He","sequence":"additional","affiliation":[{"name":"Qian Xuesen Laboratory of Space Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,11,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_1_3_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"e_1_3_2_1_6_1","volume-title":"A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282","author":"Cheng Yu","year":"2017","unstructured":"Yu Cheng , Duo Wang , Pan Zhou , and Tao Zhang . 2017. A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 ( 2017 ). Yu Cheng, Duo Wang, Pan Zhou, and Tao Zhang. 2017. A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305939"},{"key":"e_1_3_2_1_8_1","volume-title":"Soft weight-sharing for neural network compression. arXiv preprint arXiv:1702.04008","author":"Ullrich Karen","year":"2017","unstructured":"Karen Ullrich , Edward Meeds , and Max Welling . 2017. Soft weight-sharing for neural network compression. arXiv preprint arXiv:1702.04008 ( 2017 ). Karen Ullrich, Edward Meeds, and Max Welling. 2017. Soft weight-sharing for neural network compression. arXiv preprint arXiv:1702.04008 (2017)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969366"},{"key":"e_1_3_2_1_10_1","volume-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878","author":"Zhu Michael","year":"2017","unstructured":"Michael Zhu and Suyog Gupta . 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 ( 2017 ). Michael Zhu and Suyog Gupta. 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"Learning Sparse Neural Networks through L_0 Regularization. arXiv preprint arXiv:1712.01312","author":"Louizos Christos","year":"2017","unstructured":"Christos Louizos , Max Welling , and Diederik P Kingma . 2017. Learning Sparse Neural Networks through L_0 Regularization. arXiv preprint arXiv:1712.01312 ( 2017 ). Christos Louizos, Max Welling, and Diederik P Kingma. 2017. Learning Sparse Neural Networks through L_0 Regularization. arXiv preprint arXiv:1712.01312 (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"Compressing neural networks using the variational information bottleneck. arXiv preprint arXiv:1802.10399","author":"Dai Bin","year":"2018","unstructured":"Bin Dai , Chen Zhu , and David Wipf . 2018. Compressing neural networks using the variational information bottleneck. arXiv preprint arXiv:1802.10399 ( 2018 ). Bin Dai, Chen Zhu, and David Wipf. 2018. Compressing neural networks using the variational information bottleneck. arXiv preprint arXiv:1802.10399 (2018)."},{"volume-title":"Targeted Dropout. In 32nd Conference on Neural Information Processing Systems.","author":"Gomez Aidan N.","key":"e_1_3_2_1_13_1","unstructured":"Aidan N. Gomez , Ivan Zhang , Kevin Swersky , Yarin Gal , and Geoffrey E. Hinton . 2018 . Targeted Dropout. In 32nd Conference on Neural Information Processing Systems. Aidan N. Gomez, Ivan Zhang, Kevin Swersky, Yarin Gal, and Geoffrey E. Hinton. 2018. Targeted Dropout. In 32nd Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969527"},{"key":"e_1_3_2_1_15_1","volume-title":"Eunho Yang, and Sungjoo Hwang.","author":"Lee Juho","year":"2018","unstructured":"Juho Lee , Saehoon Kim , Jaehong Yoon , Hae Beom Lee , Eunho Yang, and Sungjoo Hwang. 2018 . Adaptive Network Sparsification via Dependent Variational Beta-Bernoulli Dropout . arXiv preprint arXiv:1805.10896 (2018). Juho Lee, Saehoon Kim, Jaehong Yoon, Hae Beom Lee, Eunho Yang, and Sungjoo Hwang. 2018. Adaptive Network Sparsification via Dependent Variational Beta-Bernoulli Dropout. arXiv preprint arXiv:1805.10896 (2018)."},{"volume-title":"Selected papers of hirotugu akaike","author":"Akaike Hirotogu","key":"e_1_3_2_1_16_1","unstructured":"Hirotogu Akaike . 1998. Information theory and an extension of the maximum likelihood principle . In Selected papers of hirotugu akaike . Springer , 199\u2013213. Hirotogu Akaike. 1998. Information theory and an extension of the maximum likelihood principle. In Selected papers of hirotugu akaike. Springer, 199\u2013213."},{"key":"e_1_3_2_1_17_1","volume-title":"Estimating the dimension of a model. The annals of statistics 6, 2","author":"Gideon Schwarz","year":"1978","unstructured":"Gideon Schwarz 1978. Estimating the dimension of a model. The annals of statistics 6, 2 ( 1978 ), 461\u2013464. Gideon Schwarz 1978. Estimating the dimension of a model. The annals of statistics 6, 2 (1978), 461\u2013464."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Ingrid Daubechies Michel Defrise and Christine De Mol. 2004. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences 57 11 (2004) 1413\u20131457.  Ingrid Daubechies Michel Defrise and Christine De Mol. 2004. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences 57 11 (2004) 1413\u20131457.","DOI":"10.1002\/cpa.20042"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2987061.2987082"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/109230.109298"},{"key":"e_1_3_2_1_21_1","volume-title":"Dsd: Dense-sparse-dense training for deep neural networks. arXiv preprint arXiv:1607.04381","author":"Han Song","year":"2016","unstructured":"Song Han , Jeff Pool , Sharan Narang , Huizi Mao , Enhao Gong , Shijian Tang , Erich Elsen , Peter Vajda , Manohar Paluri , John Tran , 2016 . Dsd: Dense-sparse-dense training for deep neural networks. arXiv preprint arXiv:1607.04381 (2016). Song Han, Jeff Pool, Sharan Narang, Huizi Mao, Enhao Gong, Shijian Tang, Erich Elsen, Peter Vajda, Manohar Paluri, John Tran, 2016. Dsd: Dense-sparse-dense training for deep neural networks. arXiv preprint arXiv:1607.04381 (2016)."},{"volume-title":"Integer programming: theory and practice","author":"Karlof John K","key":"e_1_3_2_1_22_1","unstructured":"John K Karlof . 2005. Integer programming: theory and practice . CRC Press . John K Karlof. 2005. Integer programming: theory and practice. CRC Press."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_24_1","first-page":"1","article-title":"Potential Game Theoretic Learning for the Minimal Weighted Vertex Cover in Distributed Networking Systems","volume":"99","author":"Sun C.","year":"2018","unstructured":"C. Sun , W. Sun , X. Wang , and Q. Zhou . 2018 . Potential Game Theoretic Learning for the Minimal Weighted Vertex Cover in Distributed Networking Systems . IEEE Transactions on Cybernetics PP , 99 (2018), 1 \u2013 11 . C. Sun, W. Sun, X. Wang, and Q. Zhou. 2018. Potential Game Theoretic Learning for the Minimal Weighted Vertex Cover in Distributed Networking Systems. IEEE Transactions on Cybernetics PP, 99 (2018), 1\u201311.","journal-title":"IEEE Transactions on Cybernetics PP"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_1_26_1","volume-title":"SNIP: Single-shot network pruning based on connection sensitivity. arXiv preprint arXiv:1810.02340","author":"Lee Namhoon","year":"2018","unstructured":"Namhoon Lee , Thalaiyasingam Ajanthan , and Philip HS Torr . 2018 . SNIP: Single-shot network pruning based on connection sensitivity. arXiv preprint arXiv:1810.02340 (2018). Namhoon Lee, Thalaiyasingam Ajanthan, and Philip HS Torr. 2018. SNIP: Single-shot network pruning based on connection sensitivity. arXiv preprint arXiv:1810.02340 (2018)."},{"key":"e_1_3_2_1_27_1","volume-title":"Hong-You Chen, Chun-Pei Yang, Shou-De Lin, and Pradeep Ravikumar.","author":"Yeh Chih-Kuan","year":"2018","unstructured":"Chih-Kuan Yeh , Ian EH Yen , Hong-You Chen, Chun-Pei Yang, Shou-De Lin, and Pradeep Ravikumar. 2018 . DEEP-TRIM: REVISITING L1 REGULARIZATION FOR CONNECTION PRUNING OF DEEP NETWORK. ( 2018). Chih-Kuan Yeh, Ian EH Yen, Hong-You Chen, Chun-Pei Yang, Shou-De Lin, and Pradeep Ravikumar. 2018. DEEP-TRIM: REVISITING L1 REGULARIZATION FOR CONNECTION PRUNING OF DEEP NETWORK. (2018)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295239"},{"key":"e_1_3_2_1_29_1","unstructured":"Wenyuan Zeng and Raquel Urtasun. 2018. MLPrune: Multi-Layer Pruning for Automated Neural Network Compression. (2018).  Wenyuan Zeng and Raquel Urtasun. 2018. MLPrune: Multi-Layer Pruning for Automated Neural Network Compression. (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157251"},{"key":"e_1_3_2_1_31_1","volume-title":"Dropout as data augmentation. arXiv preprint arXiv:1506.08700","author":"Bouthillier Xavier","year":"2015","unstructured":"Xavier Bouthillier , Kishore Konda , Pascal Vincent , and Roland Memisevic . 2015. Dropout as data augmentation. arXiv preprint arXiv:1506.08700 ( 2015 ). Xavier Bouthillier, Kishore Konda, Pascal Vincent, and Roland Memisevic. 2015. Dropout as data augmentation. arXiv preprint arXiv:1506.08700 (2015)."},{"key":"e_1_3_2_1_32_1","volume-title":"Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580","author":"Hinton Geoffrey E","year":"2012","unstructured":"Geoffrey E Hinton , Nitish Srivastava , Alex Krizhevsky , Ilya Sutskever , and Ruslan R Salakhutdinov . 2012. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 ( 2012 ). Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. 2012. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)."},{"key":"e_1_3_2_1_33_1","volume-title":"Compressing neural networks using the variational information bottleneck. arXiv preprint arXiv:1802.10399","author":"Dai Bin","year":"2018","unstructured":"Bin Dai , Chen Zhu , and David Wipf . 2018. Compressing neural networks using the variational information bottleneck. arXiv preprint arXiv:1802.10399 ( 2018 ). Bin Dai, Chen Zhu, and David Wipf. 2018. Compressing neural networks using the variational information bottleneck. arXiv preprint arXiv:1802.10399 (2018)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295116"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295422"},{"key":"e_1_3_2_1_36_1","volume-title":"Generalized dropout. arXiv preprint arXiv:1611.06791","author":"Srinivas Suraj","year":"2016","unstructured":"Suraj Srinivas and R Venkatesh Babu . 2016. Generalized dropout. arXiv preprint arXiv:1611.06791 ( 2016 ). Suraj Srinivas and R Venkatesh Babu. 2016. Generalized dropout. arXiv preprint arXiv:1611.06791 (2016)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_38_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_39_1","volume-title":"DeepTwist: Learning Model Compression via Occasional Weight Distortion. arXiv preprint arXiv:1810.12823","author":"Lee Dongsoo","year":"2018","unstructured":"Dongsoo Lee , Parichay Kapoor , and Byeongwook Kim . 2018. DeepTwist: Learning Model Compression via Occasional Weight Distortion. arXiv preprint arXiv:1810.12823 ( 2018 ). Dongsoo Lee, Parichay Kapoor, and Byeongwook Kim. 2018. DeepTwist: Learning Model Compression via Occasional Weight Distortion. arXiv preprint arXiv:1810.12823 (2018)."}],"event":{"name":"IPMV 2020: 2020 2nd International Conference on Image Processing and Machine Vision","acronym":"IPMV 2020","location":"Bangkok Thailand"},"container-title":["2020 2nd International Conference on Image Processing and Machine Vision"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3421558.3421559","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3421558.3421559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:21Z","timestamp":1750268961000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3421558.3421559"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,5]]},"references-count":39,"alternative-id":["10.1145\/3421558.3421559","10.1145\/3421558"],"URL":"https:\/\/doi.org\/10.1145\/3421558.3421559","relation":{},"subject":[],"published":{"date-parts":[[2020,8,5]]},"assertion":[{"value":"2020-11-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}