{"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/delugenets-deep-networks-with-efficient-and","title":"DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows","arxiv_id":"1611.05552","date":"2016-11-17","proceeding":null,"authors":["Jason Kuen","Xiangfei Kong","Gang Wang","Yap-Peng Tan"],"abstract":"Deluge Networks (DelugeNets) are deep neural networks which efficiently\nfacilitate massive cross-layer information inflows from preceding layers to\nsucceeding layers. The connections between layers in DelugeNets are established\nthrough cross-layer depthwise convolutional layers with learnable filters,\nacting as a flexible yet efficient selection mechanism. DelugeNets can\npropagate information across many layers with greater flexibility and utilize\nnetwork parameters more effectively compared to ResNets, whilst being more\nefficient than DenseNets. Remarkably, a DelugeNet model with just model\ncomplexity of 4.31 GigaFLOPs and 20.2M network parameters, achieve\nclassification errors of 3.76% and 19.02% on CIFAR-10 and CIFAR-100 dataset\nrespectively. Moreover, DelugeNet-122 performs competitively to ResNet-200 on\nImageNet dataset, despite costing merely half of the computations needed by the\nlatter.","url_abs":"http://arxiv.org/abs/1611.05552v5","url_pdf":"http://arxiv.org/pdf/1611.05552v5.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":"delugenets-deep-networks-with-efficient-and","repo_url":"https://github.com/xternalz/DelugeNets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}