{"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/competitive-inner-imaging-squeeze-and","title":"Competitive Inner-Imaging Squeeze and Excitation for Residual Network","arxiv_id":"1807.08920","date":"2018-07-24","proceeding":null,"authors":["Yang Hu","Guihua Wen","Mingnan Luo","Dan Dai","Jiajiong Ma","Zhiwen Yu"],"abstract":"Residual networks, which use a residual unit to supplement the identity\nmappings, enable very deep convolutional architecture to operate well, however,\nthe residual architecture has been proved to be diverse and redundant, which\nmay leads to low-efficient modeling. In this work, we propose a competitive\nsqueeze-excitation (SE) mechanism for the residual network. Re-scaling the\nvalue for each channel in this structure will be determined by the residual and\nidentity mappings jointly, and this design enables us to expand the meaning of\nchannel relationship modeling in residual blocks. Modeling of the competition\nbetween residual and identity mappings cause the identity flow to control the\ncomplement of the residual feature maps for itself. Furthermore, we design a\nnovel inner-imaging competitive SE block to shrink the consumption and re-image\nthe global features of intermediate network structure, by using the\ninner-imaging mechanism, we can model the channel-wise relations with\nconvolution in spatial. We carry out experiments on the CIFAR, SVHN, and\nImageNet datasets, and the proposed method can challenge state-of-the-art\nresults.","url_abs":"http://arxiv.org/abs/1807.08920v4","url_pdf":"http://arxiv.org/pdf/1807.08920v4.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":"competitive-inner-imaging-squeeze-and","repo_url":"https://github.com/scut-aitcm/Competitive-Inner-Imaging-SENet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}