{"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/condensenet-an-efficient-densenet-using","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","arxiv_id":"1711.09224","date":"2017-11-25","proceeding":"CVPR 2018 6","authors":["Gao Huang","Shichen Liu","Laurens van der Maaten","Kilian Q. Weinberger"],"abstract":"Deep neural networks are increasingly used on mobile devices, where\ncomputational resources are limited. In this paper we develop CondenseNet, a\nnovel network architecture with unprecedented efficiency. It combines dense\nconnectivity with a novel module called learned group convolution. The dense\nconnectivity facilitates feature re-use in the network, whereas learned group\nconvolutions remove connections between layers for which this feature re-use is\nsuperfluous. At test time, our model can be implemented using standard group\nconvolutions, allowing for efficient computation in practice. Our experiments\nshow that CondenseNets are far more efficient than state-of-the-art compact\nconvolutional networks such as MobileNets and ShuffleNets.","url_abs":"http://arxiv.org/abs/1711.09224v2","url_pdf":"http://arxiv.org/pdf/1711.09224v2.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":"condensenet-an-efficient-densenet-using","repo_url":"https://github.com/ShichenLiu/CondenseNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"condensenet-an-efficient-densenet-using","repo_url":"https://github.com/jianghaojun/CondenseNetV2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"condensenet-an-efficient-densenet-using","repo_url":"https://github.com/marload/ConvNets-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"condensenet-an-efficient-densenet-using","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"condensenet-an-efficient-densenet-using","repo_url":"https://github.com/vponcelo/CondenseNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"condensenet-an-efficient-densenet-using","repo_url":"https://github.com/zhouyuan888888/sgcpnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09224","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}