{"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/harmonic-networks-integrating-spectral","title":"Harmonic Networks: Integrating Spectral Information into CNNs","arxiv_id":"1812.03205","date":"2018-12-07","proceeding":null,"authors":["Matej Ulicny","Vladimir A. Krylov","Rozenn Dahyot"],"abstract":"Convolutional neural networks (CNNs) learn filters in order to capture local\ncorrelation patterns in feature space. In contrast, in this paper we propose\nharmonic blocks that produce features by learning optimal combinations of\nspectral filters defined by the Discrete Cosine Transform. The harmonic blocks\nare used to replace conventional convolutional layers to construct partial or\nfully harmonic CNNs. We extensively validate our approach and show that the\nintroduction of harmonic blocks into state-of-the-art CNN baseline\narchitectures results in comparable or better performance in classification\ntasks on small NORB, CIFAR10 and CIFAR100 datasets.","url_abs":"http://arxiv.org/abs/1812.03205v1","url_pdf":"http://arxiv.org/pdf/1812.03205v1.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":"harmonic-networks-integrating-spectral","repo_url":"https://github.com/matej-ulicny/harmonic-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"discrete-cosine-transform","method_name":"Discrete Cosine Transform"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}