{"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/gabornet-gabor-filters-with-learnable","title":"GaborNet: Gabor filters with learnable parameters in deep convolutional neural networks","arxiv_id":"1904.13204","date":"2019-04-30","proceeding":null,"authors":["Andrey Alekseev","Anatoly Bobe"],"abstract":"The article describes a system for image recognition using deep convolutional\nneural networks. Modified network architecture is proposed that focuses on\nimproving convergence and reducing training complexity. The filters in the\nfirst layer of the network are constrained to fit the Gabor function. The\nparameters of Gabor functions are learnable and are updated by standard\nbackpropagation techniques. The system was implemented on Python, tested on\nseveral datasets and outperformed the common convolutional networks.","url_abs":"http://arxiv.org/abs/1904.13204v1","url_pdf":"http://arxiv.org/pdf/1904.13204v1.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":"gabornet-gabor-filters-with-learnable","repo_url":"https://github.com/iKintosh/GaborNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.13204","atlas_url":"https://app.syntology.ai/?focus=1904.13204","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}