{"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/mixed-link-networks","title":"Mixed Link Networks","arxiv_id":"1802.01808","date":"2018-02-06","proceeding":null,"authors":["Wenhai Wang","Xiang Li","Jian Yang","Tong Lu"],"abstract":"Basing on the analysis by revealing the equivalence of modern networks, we\nfind that both ResNet and DenseNet are essentially derived from the same \"dense\ntopology\", yet they only differ in the form of connection -- addition (dubbed\n\"inner link\") vs. concatenation (dubbed \"outer link\"). However, both two forms\nof connections have the superiority and insufficiency. To combine their\nadvantages and avoid certain limitations on representation learning, we present\na highly efficient and modularized Mixed Link Network (MixNet) which is\nequipped with flexible inner link and outer link modules. Consequently, ResNet,\nDenseNet and Dual Path Network (DPN) can be regarded as a special case of\nMixNet, respectively. Furthermore, we demonstrate that MixNets can achieve\nsuperior efficiency in parameter over the state-of-the-art architectures on\nmany competitive datasets like CIFAR-10/100, SVHN and ImageNet.","url_abs":"http://arxiv.org/abs/1802.01808v1","url_pdf":"http://arxiv.org/pdf/1802.01808v1.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":"mixed-link-networks","repo_url":"https://github.com/DeepInsight-PCALab/MixNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"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":"https://app.syntology.ai/?focus=1802.01808","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}