{"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/building-efficient-convnets-using-redundant","title":"Building Efficient ConvNets using Redundant Feature Pruning","arxiv_id":"1802.07653","date":"2018-02-21","proceeding":null,"authors":["Babajide O. Ayinde","Jacek M. Zurada"],"abstract":"This paper presents an efficient technique to prune deep and/or wide\nconvolutional neural network models by eliminating redundant features (or\nfilters). Previous studies have shown that over-sized deep neural network\nmodels tend to produce a lot of redundant features that are either shifted\nversion of one another or are very similar and show little or no variations;\nthus resulting in filtering redundancy. We propose to prune these redundant\nfeatures along with their connecting feature maps according to their\ndifferentiation and based on their relative cosine distances in the feature\nspace, thus yielding smaller network size with reduced inference costs and\ncompetitive performance. We empirically show on select models and CIFAR-10\ndataset that inference costs can be reduced by 40% for VGG-16, 27% for\nResNet-56, and 39% for ResNet-110.","url_abs":"http://arxiv.org/abs/1802.07653v1","url_pdf":"http://arxiv.org/pdf/1802.07653v1.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":"building-efficient-convnets-using-redundant","repo_url":"https://github.com/babajide07/Redundant-Feature-Pruning-Pytorch-Implementation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"building-efficient-convnets-using-redundant","repo_url":"https://github.com/bemova/Building-Efficient-ConvNets-using-Redundant-Feature-Pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}