{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-network-compression-using-higher-order","title":"Neural Network Compression Using Higher-Order Statistics and AuxiliaryReconstruction Losses","arxiv_id":null,"date":"2020-06-15","proceeding":null,"authors":["Christos Chatzikonstantinou","Georgios Th. Papadopoulos","Kosmas Dimitropoulos","Petros Daras"],"abstract":"In this paper, the problem of pruning and compressingthe weights of various layers of deep neural networks is in-vestigated. The proposed method aims to remove redundantfilters from the network to reduce computational complex-ity and storage requirements, while improving the perfor-mance of the original network. More specifically, a novelfilter selection criterion is introduced based on the fact thatfilters whose weights follow a Gaussian distribution corre-spond to hidden units that do not capture important aspectsof data.  To this end, Higher Order Statistics (HOS) areused and filters with low cumulant values that do not de-viate significantly from Gaussian distribution are identifiedand removed from the network. In addition, a novel prun-ing strategy is proposed aiming to decide on the pruningratio of each layer using the Shapiro-Wilk normality test.The use of auxiliary MSE losses (intermediate and afterthe softmax layer) during the fine-tuning phase further im-proves the overall performance of the compressed network.Extensive experiments with different network architecturesand comparison with state-of-the-art approaches on well-known public datasets, such as CIFAR-10, CIFAR-100 andILSCVR-12, demonstrate the great potential of the proposedapproach.","url_abs":"https://openaccess.thecvf.com/content_CVPRW_2020/html/w40/Chatzikonstantinou_Neural_Network_Compression_Using_Higher-Order_Statistics_and_Auxiliary_Reconstruction_Losses_CVPRW_2020_paper.html","url_pdf":"https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Chatzikonstantinou_Neural_Network_Compression_Using_Higher-Order_Statistics_and_Auxiliary_Reconstruction_Losses_CVPRW_2020_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-network-compression-using-higher-order","repo_url":"https://github.com/chatzikon/DNN-COMPRESSION","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"neural-network-compression","task_name":"Neural Network Compression"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}