{"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/cnn-filter-db-an-empirical-investigation-of","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","arxiv_id":"2203.15331","date":"2022-03-29","proceeding":"CVPR 2022 1","authors":["Paul Gavrikov","Janis Keuper"],"abstract":"Currently, many theoretical as well as practically relevant questions towards the transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved. While ongoing research efforts are engaging these problems from various angles, in most computer vision related cases these approaches can be generalized to investigations of the effects of distribution shifts in image data. In this context, we propose to study the shifts in the learned weights of trained CNN models. Here we focus on the properties of the distributions of dominantly used 3x3 convolution filter kernels. We collected and publicly provide a dataset with over 1.4 billion filters from hundreds of trained CNNs, using a wide range of datasets, architectures, and vision tasks. In a first use case of the proposed dataset, we can show highly relevant properties of many publicly available pre-trained models for practical applications: I) We analyze distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like visual category of the dataset, task, architecture, or layer depth. Based on these results, we conclude that model pre-training can succeed on arbitrary datasets if they meet size and variance conditions. II) We show that many pre-trained models contain degenerated filters which make them less robust and less suitable for fine-tuning on target applications. Data & Project website: https://github.com/paulgavrikov/cnn-filter-db","url_abs":"https://arxiv.org/abs/2203.15331v2","url_pdf":"https://arxiv.org/pdf/2203.15331v2.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":"cnn-filter-db-an-empirical-investigation-of","repo_url":"https://github.com/paulgavrikov/cnn-filter-db","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[{"slug":"cnn-filter-db","name":"CNN Filter DB","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-9","rank_in_archive_order":148,"of":265,"metrics":{"Percentage correct":"94.79"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ResNet-9","rank_in_archive_order":152,"of":211,"metrics":{"Percentage correct":"75.59"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-fashion-mnist","task":"Image Classification","dataset":"Fashion-MNIST","model":"Inception v3","rank_in_archive_order":5,"of":34,"metrics":{"Accuracy":"94.44","Percentage error":"5.56"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-kuzushiji-mnist","task":"Image Classification","dataset":"Kuzushiji-MNIST","model":"ResNet-14","rank_in_archive_order":11,"of":26,"metrics":{"Accuracy":"98.75"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"ResNet-9","rank_in_archive_order":66,"of":81,"metrics":{"Accuracy":"99.68"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.15331","atlas_url":"https://app.syntology.ai/?focus=2203.15331","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.15331"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.15331\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.15331"},"call":"get_concepts_for_paper(arxiv_id=\"2203.15331\")"}],"by_repo":[{"repo":"paulgavrikov/cnn-filter-db","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"45c19599c484ccb55204c25366f992961ded3f1e1262d741b574afae09891ac8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}