{"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/interleaved-group-convolutions-for-deep","title":"Interleaved Group Convolutions for Deep Neural Networks","arxiv_id":"1707.02725","date":"2017-07-10","proceeding":null,"authors":["Ting Zhang","Guo-Jun Qi","Bin Xiao","Jingdong Wang"],"abstract":"In this paper, we present a simple and modularized neural network\narchitecture, named interleaved group convolutional neural networks (IGCNets).\nThe main point lies in a novel building block, a pair of two successive\ninterleaved group convolutions: primary group convolution and secondary group\nconvolution. The two group convolutions are complementary: (i) the convolution\non each partition in primary group convolution is a spatial convolution, while\non each partition in secondary group convolution, the convolution is a\npoint-wise convolution; (ii) the channels in the same secondary partition come\nfrom different primary partitions. We discuss one representative advantage:\nWider than a regular convolution with the number of parameters and the\ncomputation complexity preserved. We also show that regular convolutions, group\nconvolution with summation fusion, and the Xception block are special cases of\ninterleaved group convolutions. Empirical results over standard benchmarks,\nCIFAR-$10$, CIFAR-$100$, SVHN and ImageNet demonstrate that our networks are\nmore efficient in using parameters and computation complexity with similar or\nhigher accuracy.","url_abs":"http://arxiv.org/abs/1707.02725v2","url_pdf":"http://arxiv.org/pdf/1707.02725v2.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":"interleaved-group-convolutions-for-deep","repo_url":"https://github.com/homles11/IGCV3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"interleaved-group-convolutions-for-deep","repo_url":"https://github.com/xxradon/IGCV3-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"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":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}