{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/harmonic-networks-with-limited-training","title":"Harmonic Networks with Limited Training Samples","arxiv_id":"1905.00135","date":"2019-04-30","proceeding":null,"authors":["Matej Ulicny","Vladimir A. Krylov","Rozenn Dahyot"],"abstract":"Convolutional neural networks (CNNs) are very popular nowadays for image\nprocessing. CNNs allow one to learn optimal filters in a (mostly) supervised\nmachine learning context. However this typically requires abundant labelled\ntraining data to estimate the filter parameters. Alternative strategies have\nbeen deployed for reducing the number of parameters and / or filters to be\nlearned and thus decrease overfitting. In the context of reverting to preset\nfilters, we propose here a computationally efficient harmonic block that uses\nDiscrete Cosine Transform (DCT) filters in CNNs. In this work we examine the\nperformance of harmonic networks in limited training data scenario. We validate\nexperimentally that its performance compares well against scattering networks\nthat use wavelets as preset filters.","url_abs":"http://arxiv.org/abs/1905.00135v1","url_pdf":"http://arxiv.org/pdf/1905.00135v1.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-with-limited-training","repo_url":"https://github.com/matej-ulicny/harmonic-networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"Harmonic WRN-16-8","rank_in_archive_order":33,"of":117,"metrics":{"Percentage correct":"90.45"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"matej-ulicny/harmonic-networks","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2001.06570"],"harvested_for_calls":[{"arxiv_id":"2001.06570","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2001.06570"},"call":"get_harvested_code_for_paper(arxiv_id=\"2001.06570\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b59784ac2ddde38bd8d8e00535fa9069de7bff7780c941d82330ae2ebc8bb902","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}