{"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/residual-convolutional-neural-network","title":"Residual Convolutional Neural Network Revisited with Active Weighted Mapping","arxiv_id":"1811.06878","date":"2018-11-16","proceeding":null,"authors":["Jung HyoungHo","Lee Ryong","Lee Sanghwan","Hwang Wonjun"],"abstract":"In visual recognition, the key to the performance improvement of ResNet is\nthe success in establishing the stack of deep sequential convolutional layers\nusing identical mapping by a shortcut connection. It results in multiple paths\nof data flow under a network and the paths are merged with the equal weights.\nHowever, it is questionable whether it is correct to use the fixed and\npredefined weights at the mapping units of all paths. In this paper, we\nintroduce the active weighted mapping method which infers proper weight values\nbased on the characteristic of input data on the fly. The weight values of each\nmapping unit are not fixed but changed as the input image is changed, and the\nmost proper weight values for each mapping unit are derived according to the\ninput image. For this purpose, channel-wise information is embedded from both\nthe shortcut connection and convolutional block, and then the fully connected\nlayers are used to estimate the weight values for the mapping units. We train\nthe backbone network and the proposed module alternately for a more stable\nlearning of the proposed method. Results of the extensive experiments show that\nthe proposed method works successfully on the various backbone architectures\nfrom ResNet to DenseNet. We also verify the superiority and generality of the\nproposed method on various datasets in comparison with the baseline.","url_abs":"http://arxiv.org/abs/1811.06878v1","url_pdf":"http://arxiv.org/pdf/1811.06878v1.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":"residual-convolutional-neural-network","repo_url":"https://github.com/ChaofWang/AWSRN","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":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"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":"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":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"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}