{"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/convolutional-neural-networks-with-layer","title":"Convolutional Neural Networks with Layer Reuse","arxiv_id":"1901.09615","date":"2019-01-28","proceeding":null,"authors":["Okan Köpüklü","Maryam Babaee","Stefan Hörmann","Gerhard Rigoll"],"abstract":"A convolutional layer in a Convolutional Neural Network (CNN) consists of\nmany filters which apply convolution operation to the input, capture some\nspecial patterns and pass the result to the next layer. If the same patterns\nalso occur at the deeper layers of the network, why wouldn't the same\nconvolutional filters be used also in those layers? In this paper, we propose a\nCNN architecture, Layer Reuse Network (LruNet), where the convolutional layers\nare used repeatedly without the need of introducing new layers to get a better\nperformance. This approach introduces several advantages: (i) Considerable\namount of parameters are saved since we are reusing the layers instead of\nintroducing new layers, (ii) the Memory Access Cost (MAC) can be reduced since\nreused layer parameters can be fetched only once, (iii) the number of\nnonlinearities increases with layer reuse, and (iv) reused layers get gradient\nupdates from multiple parts of the network. The proposed approach is evaluated\non CIFAR-10, CIFAR-100 and Fashion-MNIST datasets for image classification\ntask, and layer reuse improves the performance by 5.14%, 5.85% and 2.29%,\nrespectively. The source code and pretrained models are publicly available.","url_abs":"http://arxiv.org/abs/1901.09615v2","url_pdf":"http://arxiv.org/pdf/1901.09615v2.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":"convolutional-neural-networks-with-layer","repo_url":"https://github.com/okankop/CNN-layer-reuse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}