{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:32:11Z","timestamp":1764174731356,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,12,19]],"date-time":"2019-12-19T00:00:00Z","timestamp":1576713600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6187601"],"award-info":[{"award-number":["6187601"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,12,19]]},"DOI":"10.1145\/3371425.3371481","type":"proceedings-article","created":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T13:18:36Z","timestamp":1575983916000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["On pruned, quantized and compact CNN architectures for vision applications"],"prefix":"10.1145","author":[{"given":"Pius Kwao","family":"Gadosey","sequence":"first","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujian","family":"Li","sequence":"additional","affiliation":[{"name":"Guilin University of Electronic, Technology, Guilin, Guangxi"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter T","family":"Yamak","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,12,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_2_1","first-page":"1","article-title":"ImageNet Classification with Deep Convolutional Neural","author":"Krizhevsky A","year":"2012","unstructured":"A Krizhevsky , I Sutskever and G E Hinton ( 2012 ). ImageNet Classification with Deep Convolutional Neural Networks. Adv. Neural Inf. Process. Syst. , pp. 1 -- 9 . A Krizhevsky, I Sutskever and G E Hinton (2012). ImageNet Classification with Deep Convolutional Neural Networks. Adv. Neural Inf. Process. Syst., pp. 1--9.","journal-title":"Networks. Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_3_1","first-page":"1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan K","year":"2014","unstructured":"K Simonyan and A Zisserman ( 2014 ). Very Deep Convolutional Networks for Large-Scale Image Recognition . pp. 1 -- 14 . K Simonyan and A Zisserman (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. pp. 1--14."},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"He K","year":"2016","unstructured":"K He , X Zhang , S Ren and J Sun ( 2016 ). Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). K He, X Zhang, S Ren and J Sun (2016). Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"issue":"1","key":"e_1_3_2_1_7_1","first-page":"598","article-title":"Optimal Brain Damage","volume":"2","author":"Le Cun Y","year":"1990","unstructured":"Y Le Cun , J S Denker and S A Solla ( 1990 ). Optimal Brain Damage . Adv. Neural Inf. Process. Syst. , vol. 2 , no. 1 , pp. 598 -- 605 . Y Le Cun, J S Denker and S A Solla (1990). Optimal Brain Damage. Adv. Neural Inf. Process. Syst., vol. 2, no. 1, pp. 598--605.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_8_1","first-page":"1","author":"Li H","year":"2016","unstructured":"H Li , A Kadav , I Durdanovic , H Samet and H P Graf ( 2016 ). Pruning Filters for Efficient ConvNets. No. 2016, pp. 1 -- 13 . H Li, A Kadav, I Durdanovic, H Samet and H P Graf (2016). Pruning Filters for Efficient ConvNets. No. 2016, pp. 1--13.","journal-title":"Pruning Filters for Efficient ConvNets."},{"key":"e_1_3_2_1_9_1","volume-title":"Compression-aware Training of Deep Networks. No. Nips","author":"Alvarez J M","year":"2017","unstructured":"J M Alvarez and M Salzmann ( 2017 ). Compression-aware Training of Deep Networks. No. Nips . J M Alvarez and M Salzmann (2017). Compression-aware Training of Deep Networks. No. Nips."},{"key":"e_1_3_2_1_10_1","volume-title":"K Q Weinberger and Y Chen","author":"Chen W","year":"2015","unstructured":"W Chen , J T Wilson , S Tyree , K Q Weinberger and Y Chen ( 2015 ). Compressing Neural Networks with the Hashing Trick . W Chen, J T Wilson, S Tyree, K Q Weinberger and Y Chen (2015). Compressing Neural Networks with the Hashing Trick."},{"key":"e_1_3_2_1_11_1","first-page":"1","volume-title":"W J Dally and K Keutzer","author":"Iandola F N","year":"2016","unstructured":"F N Iandola , S Han , M W Moskewicz , K Ashraf , W J Dally and K Keutzer ( 2016 ). SqueezeNet : Alex Net-level accuracy with 50x fewer parameters and <0.5MB model size. pp. 1 -- 13 . F N Iandola, S Han, M W Moskewicz, K Ashraf, W J Dally and K Keutzer (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. pp. 1--13."},{"key":"e_1_3_2_1_12_1","first-page":"1","volume-title":"M Yang and L Bourdev","author":"Gong Y","year":"2014","unstructured":"Y Gong , L Liu , M Yang and L Bourdev ( 2014 ). Compressing Deep Convolutional Networks using Vector Quantization . pp. 1 -- 10 , 2014. Y Gong, L Liu, M Yang and L Bourdev (2014). Compressing Deep Convolutional Networks using Vector Quantization. pp. 1--10, 2014."},{"key":"e_1_3_2_1_13_1","volume-title":"R Ge and T Ma","author":"Arora S","year":"2013","unstructured":"S Arora , A Bhaskara , R Ge and T Ma ( 2013 ). Provable Bounds for Learning Some Deep Representations . S Arora, A Bhaskara, R Ge and T Ma (2013). Provable Bounds for Learning Some Deep Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017","volume":"10","author":"Liu W","year":"2017","unstructured":"W Liu , ( 2017 ). Hybrid Pruning: Thinner Sparse Networks for Fast Inference on Edge Devices . Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017 , vol. 2017-Janua, no. September, pp. 1-- 10 . W Liu, et al. (2017). Hybrid Pruning: Thinner Sparse Networks for Fast Inference on Edge Devices. Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, no. September, pp. 1--10."},{"key":"e_1_3_2_1_15_1","volume-title":"H Wen and Y Zou","author":"Zhou S","year":"2016","unstructured":"S Zhou , Y Wu , Z Ni , X Zhou , H Wen and Y Zou ( 2016 ). DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients . Vol. 1 , no. 1. S Zhou, Y Wu, Z Ni, X Zhou, H Wen and Y Zou (2016). DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. Vol. 1, no. 1."},{"key":"e_1_3_2_1_16_1","first-page":"1","volume-title":"Trained Ternary Quantization","author":"Zhu C","year":"2016","unstructured":"C Zhu , S Han , H.Mao and W J Dally ( 2016 ). Trained Ternary Quantization . pp. 1 -- 10 . C Zhu, S Han, H.Mao and W J Dally (2016). Trained Ternary Quantization. pp. 1--10."},{"key":"e_1_3_2_1_17_1","unstructured":"A G Howard etal (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.  A G Howard et al. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications."},{"key":"e_1_3_2_1_18_1","volume-title":"A Zhmoginov and L C Chen","author":"Sandler M","year":"2018","unstructured":"M Sandler , A Howard , M Zhu , A Zhmoginov and L C Chen ( 2018 ). MobileNetV2: Inverted Residuals and Linear Bottlenecks . M Sandler, A Howard, M Zhu, A Zhmoginov and L C Chen (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks."},{"key":"e_1_3_2_1_19_1","volume-title":"M Lin and J Sun","author":"Zhang X","year":"2017","unstructured":"X Zhang , M Lin and J Sun ( 2017 ). ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices . X Zhang, M Lin and J Sun (2017). ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices."},{"key":"e_1_3_2_1_20_1","first-page":"1","volume-title":"L Yang and D Shin","author":"Kim Y D","year":"2015","unstructured":"Y D Kim , E Park , S Yoo , T Choi , L Yang and D Shin ( 2015 ). Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications . pp. 1 -- 16 . Y D Kim, E Park, S Yoo, T Choi, L Yang and D Shin (2015). Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications. pp. 1--16."},{"key":"e_1_3_2_1_21_1","unstructured":"L Sifre and S Mallat (2014). PhD Thesis Ecole Polytechnique CMAP Rigid-Motion Scattering For Image Classification.  L Sifre and S Mallat (2014). PhD Thesis Ecole Polytechnique CMAP Rigid-Motion Scattering For Image Classification."},{"key":"e_1_3_2_1_22_1","first-page":"1","volume-title":"M Ranzato and N de Freitas","author":"Denil M","year":"2013","unstructured":"M Denil , B Shakibi , L Dinh , M Ranzato and N de Freitas ( 2013 ). Predicting Parameters in Deep Learning . pp. 1 -- 9 . M Denil, B Shakibi, L Dinh, M Ranzato and N de Freitas (2013). Predicting Parameters in Deep Learning. pp. 1--9."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"e_1_3_2_1_25_1","first-page":"1","volume-title":"No.","author":"Molchanov P","year":"2016","unstructured":"P Molchanov , S Tyree , T Karras , T Aila and J Kautz ( 2016 ). Pruning Convolutional Neural Networks for Resource Efficient Inference . No. 2015, pp. 1 -- 17 . P Molchanov, S Tyree, T Karras, T Aila and J Kautz (2016). Pruning Convolutional Neural Networks for Resource Efficient Inference. No. 2015, pp. 1--17."},{"key":"e_1_3_2_1_26_1","volume-title":"B Zhang and B Liu","author":"Li F","year":"2016","unstructured":"F Li , B Zhang and B Liu ( 2016 ). Ternary Weight Networks. No. Nips . F Li, B Zhang and B Liu (2016). Ternary Weight Networks. No. Nips."},{"key":"e_1_3_2_1_27_1","volume-title":"X Chen and Y Peng","author":"Qin Z","year":"2018","unstructured":"Z Qin , Z Zhang , X Chen and Y Peng ( 2018 ). FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy . Z Qin, Z Zhang, X Chen and Y Peng (2018). FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy."},{"key":"e_1_3_2_1_28_1","unstructured":"L Sifre and S Mallat (2014). PhD Thesis Ecole Polytechnique CMAP Rigid-Motion Scattering For Image Classification.  L Sifre and S Mallat (2014). PhD Thesis Ecole Polytechnique CMAP Rigid-Motion Scattering For Image Classification."},{"key":"e_1_3_2_1_29_1","volume-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"Ioffe S","year":"2015","unstructured":"S Ioffe and C Szegedy ( 2015 ). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift . S Ioffe and C Szegedy (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift."},{"key":"e_1_3_2_1_30_1","first-page":"1","volume-title":"No. Nips","author":"Paszke A","year":"2017","unstructured":"A Paszke , ( 2017 ). Automatic differentiation in PyTorch . No. Nips , pp. 1 -- 4 . A Paszke, et al. (2017). Automatic differentiation in PyTorch. No. Nips, pp. 1--4."},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Caltech-UCSD birds 200","volume":"200","author":"Welinder P","year":"2010","unstructured":"P Welinder , S Branson , T Mita and C Wah ( 2010 ). Caltech-UCSD birds 200 . CalTech , vol. 200 , pp. 1 -- 15 . P Welinder, S Branson, T Mita and C Wah (2010). Caltech-UCSD birds 200. CalTech, vol. 200, pp. 1--15.","journal-title":"CalTech"},{"key":"e_1_3_2_1_32_1","volume-title":"A Holub and P Perona","author":"Griffin G","year":"2007","unstructured":"G Griffin , A Holub and P Perona ( 2007 ). Caltech-256 object category dataset. Caltech mimeo, vol. 11 , no. 1, pp. 20. G Griffin, A Holub and P Perona (2007). Caltech-256 object category dataset. Caltech mimeo, vol. 11, no. 1, pp. 20."},{"key":"e_1_3_2_1_33_1","volume-title":"Automated flower classification over a large number of classes","author":"Nilsback M","year":"2008","unstructured":"M Nilsback and A Zisserman ( 2008 ). Automated flower classification over a large number of classes . M Nilsback and A Zisserman (2008). Automated flower classification over a large number of classes."},{"key":"e_1_3_2_1_34_1","first-page":"164","volume-title":"Second order derivaties for network prunning: Optimal brain surgeon. Adv. NIPS5","author":"Hassibi B","year":"1993","unstructured":"B Hassibi and D Stork ( 1993 ). Second order derivaties for network prunning: Optimal brain surgeon. Adv. NIPS5 , pp. 164 -- 171 . B Hassibi and D Stork (1993). Second order derivaties for network prunning: Optimal brain surgeon. Adv. NIPS5, pp. 164--171."},{"key":"e_1_3_2_1_35_1","first-page":"1","volume-title":"A Osokin and D Vetrov","author":"Novikov A","year":"2015","unstructured":"A Novikov , D Podoprikhin , A Osokin and D Vetrov ( 2015 ). Tensorizing Neural Networks . pp. 1 -- 9 . A Novikov, D Podoprikhin, A Osokin and D Vetrov (2015). Tensorizing Neural Networks. pp. 1--9."}],"event":{"name":"AIIPCC '19: 2019 International Conference on Artificial Intelligence, Information Processing and Cloud Computing","sponsor":["ASciE Association for Science and Engineering"],"location":"Sanya China","acronym":"AIIPCC '19"},"container-title":["Proceedings of the International Conference on Artificial Intelligence, Information Processing and Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3371425.3371481","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3371425.3371481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:23Z","timestamp":1750203863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3371425.3371481"}},"subtitle":["an empirical study"],"short-title":[],"issued":{"date-parts":[[2019,12,19]]},"references-count":35,"alternative-id":["10.1145\/3371425.3371481","10.1145\/3371425"],"URL":"https:\/\/doi.org\/10.1145\/3371425.3371481","relation":{},"subject":[],"published":{"date-parts":[[2019,12,19]]},"assertion":[{"value":"2019-12-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}