{"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/improving-fractal-pre-training","title":"Improving Fractal Pre-training","arxiv_id":"2110.03091","date":"2021-10-06","proceeding":null,"authors":["Connor Anderson","Ryan Farrell"],"abstract":"The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The process of creating and curating such a dataset is a monumental undertaking, demanding extensive effort and labelling expense and necessitating careful navigation of technical and social issues such as label accuracy, copyright ownership, and content bias. What if we had a way to harness the power of large image datasets but with few or none of the major issues and concerns currently faced? This paper extends the recent work of Kataoka et. al. (2020), proposing an improved pre-training dataset based on dynamically-generated fractal images. Challenging issues with large-scale image datasets become points of elegance for fractal pre-training: perfect label accuracy at zero cost; no need to store/transmit large image archives; no privacy/demographic bias/concerns of inappropriate content, as no humans are pictured; limitless supply and diversity of images; and the images are free/open-source. Perhaps surprisingly, avoiding these difficulties imposes only a small penalty in performance. Leveraging a newly-proposed pre-training task -- multi-instance prediction -- our experiments demonstrate that fine-tuning a network pre-trained using fractals attains 92.7-98.1\\% of the accuracy of an ImageNet pre-trained network.","url_abs":"https://arxiv.org/abs/2110.03091v1","url_pdf":"https://arxiv.org/pdf/2110.03091v1.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":"improving-fractal-pre-training","repo_url":"https://github.com/catalys1/fractal-pretraining","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.03091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03091"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/catalys1/fractal-pretraining","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":8},"by_repo_kind":{"listed":{"samples":9,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a1c6321806632355","entry":"sample_svs","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/fractals/ifs.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/fractals/ifs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1c6321806632355"}},{"code_sha256_prefix":"7b3c800308a296cc","entry":"first_layer","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/training/makegif.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/training/makegif.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b3c800308a296cc"}},{"code_sha256_prefix":"a9b449b9f5ea02ea","entry":"mixup","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/training/model/glas.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/training/model/glas.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9b449b9f5ea02ea"}},{"code_sha256_prefix":"f30e579115d56847","entry":"normalization","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/training/datamodule/utils.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/training/datamodule/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f30e579115d56847"}},{"code_sha256_prefix":"5f418a339c996a9b","entry":"sample_svs_rej","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/fractals/ifs.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/fractals/ifs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f418a339c996a9b"}},{"code_sha256_prefix":"eea2210acf08765a","entry":"sample_system","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/fractals/ifs.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/fractals/ifs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eea2210acf08765a"}},{"code_sha256_prefix":"15b863dcd6f5736e","entry":"to_img","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/training/makegif.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/training/makegif.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15b863dcd6f5736e"}},{"code_sha256_prefix":"be5ca2dd5662a48d","entry":"to_tensor","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/training/datamodule/utils.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/training/datamodule/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be5ca2dd5662a48d"}},{"code_sha256_prefix":"7001f0a9cc01d6bc","entry":"val_collate_fn","repo":"catalys1/fractal-pretraining","repo_kind":"listed","path":"fractal_learning/training/datamodule/medseg_datamodule.py","file_url":"https://github.com/catalys1/fractal-pretraining/blob/HEAD/fractal_learning/training/datamodule/medseg_datamodule.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7001f0a9cc01d6bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}