{"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/rethinking-layer-wise-feature-amounts-in","title":"Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures","arxiv_id":"1812.05836","date":"2018-12-14","proceeding":null,"authors":["Martin Mundt","Sagnik Majumder","Tobias Weis","Visvanathan Ramesh"],"abstract":"We characterize convolutional neural networks with respect to the relative\namount of features per layer. Using a skew normal distribution as a\nparametrized framework, we investigate the common assumption of monotonously\nincreasing feature-counts with higher layers of architecture designs. Our\nevaluation on models with VGG-type layers on the MNIST, Fashion-MNIST and\nCIFAR-10 image classification benchmarks provides evidence that motivates\nrethinking of our common assumption: architectures that favor larger early\nlayers seem to yield better accuracy.","url_abs":"http://arxiv.org/abs/1812.05836v1","url_pdf":"http://arxiv.org/pdf/1812.05836v1.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":"rethinking-layer-wise-feature-amounts-in","repo_url":"https://github.com/MrtnMndt/Rethinking_CNN_Layerwise_Feature_Amounts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-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}