{"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/heneta-highly-efficient-convolutional-neural","title":"HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage","arxiv_id":"1803.02742","date":"2018-03-07","proceeding":null,"authors":["Qiuyu Zhu","Ruixin Zhang"],"abstract":"In order to enhance the real-time performance of convolutional neural\nnetworks(CNNs), more and more researchers are focusing on improving the\nefficiency of CNN. Based on the analysis of some CNN architectures, such as\nResNet, DenseNet, ShuffleNet and so on, we combined their advantages and\nproposed a very efficient model called Highly Efficient Networks(HENet). The\nnew architecture uses an unusual way to combine group convolution and channel\nshuffle which was mentioned in ShuffleNet. Inspired by ResNet and DenseNet, we\nalso proposed a new way to use element-wise addition and concatenation\nconnection with each block. In order to make greater use of feature maps,\npooling operations are removed from HENet. The experiments show that our\nmodel's efficiency is more than 1 times higher than ShuffleNet on many open\nsource datasets, such as CIFAR-10/100 and SVHN.","url_abs":"http://arxiv.org/abs/1803.02742v2","url_pdf":"http://arxiv.org/pdf/1803.02742v2.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":"heneta-highly-efficient-convolutional-neural","repo_url":"https://github.com/anlongstory/HENet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"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-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"shufflenet","method_name":"ShuffleNet"},{"method_slug":"shufflenet-block","method_name":"ShuffleNet Block"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.02742","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}