{"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/polynet-a-pursuit-of-structural-diversity-in","title":"PolyNet: A Pursuit of Structural Diversity in Very Deep Networks","arxiv_id":"1611.05725","date":"2016-11-17","proceeding":"CVPR 2017 7","authors":["Xingcheng Zhang","Zhizhong Li","Chen Change Loy","Dahua Lin"],"abstract":"A number of studies have shown that increasing the depth or width of\nconvolutional networks is a rewarding approach to improve the performance of\nimage recognition. In our study, however, we observed difficulties along both\ndirections. On one hand, the pursuit for very deep networks is met with a\ndiminishing return and increased training difficulty; on the other hand,\nwidening a network would result in a quadratic growth in both computational\ncost and memory demand. These difficulties motivate us to explore structural\ndiversity in designing deep networks, a new dimension beyond just depth and\nwidth. Specifically, we present a new family of modules, namely the\nPolyInception, which can be flexibly inserted in isolation or in a composition\nas replacements of different parts of a network. Choosing PolyInception modules\nwith the guidance of architectural efficiency can improve the expressive power\nwhile preserving comparable computational cost. The Very Deep PolyNet, designed\nfollowing this direction, demonstrates substantial improvements over the\nstate-of-the-art on the ILSVRC 2012 benchmark. Compared to Inception-ResNet-v2,\nit reduces the top-5 validation error on single crops from 4.9% to 4.25%, and\nthat on multi-crops from 3.7% to 3.45%.","url_abs":"http://arxiv.org/abs/1611.05725v2","url_pdf":"http://arxiv.org/pdf/1611.05725v2.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":"polynet-a-pursuit-of-structural-diversity-in","repo_url":"https://github.com/CUHK-MMLAB/polynet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"polynet-a-pursuit-of-structural-diversity-in","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":"polynet-a-pursuit-of-structural-diversity-in","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"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"inception-resnet-v2","method_name":"Inception-ResNet-v2"},{"method_slug":"inception-resnet-v2-reduction-b","method_name":"Inception-ResNet-v2 Reduction-B"},{"method_slug":"inception-resnet-v2-a","method_name":"Inception-ResNet-v2-A"},{"method_slug":"inception-resnet-v2-b","method_name":"Inception-ResNet-v2-B"},{"method_slug":"inception-resnet-v2-c","method_name":"Inception-ResNet-v2-C"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"reduction-a","method_name":"Reduction-A"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.05725","atlas_url":"https://app.syntology.ai/?focus=1611.05725","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}