{"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/cytoimagenet-a-large-scale-pretraining","title":"CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning","arxiv_id":"2111.11646","date":"2021-11-23","proceeding":null,"authors":["Stanley Bryan Z. Hua","Alex X. Lu","Alan M. Moses"],"abstract":"Motivation: In recent years, image-based biological assays have steadily become high-throughput, sparking a need for fast automated methods to extract biologically-meaningful information from hundreds of thousands of images. Taking inspiration from the success of ImageNet, we curate CytoImageNet, a large-scale dataset of openly-sourced and weakly-labeled microscopy images (890K images, 894 classes). Pretraining on CytoImageNet yields features that are competitive to ImageNet features on downstream microscopy classification tasks. We show evidence that CytoImageNet features capture information not available in ImageNet-trained features. The dataset is made available at https://www.kaggle.com/stanleyhua/cytoimagenet.","url_abs":"https://arxiv.org/abs/2111.11646v2","url_pdf":"https://arxiv.org/pdf/2111.11646v2.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":"cytoimagenet-a-large-scale-pretraining","repo_url":"https://github.com/stan-hua/CytoImageNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"bbbc021-nsc-accuracy","task_name":"BBBC021 NSC Accuracy"},{"task_slug":null,"task_name":"COOS-7 Accuracy"},{"task_slug":"cyclops-accuracy","task_name":"CYCLoPs Accuracy"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"cytoimagenet","name":"CytoImageNet","full_name":"CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.11646"}},"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":"deterministic:regex_extraction","url":"https://github.com/stan-hua/CytoImageNet","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"c3f5f451d82f6b9c","entry":"exists_meta","repo":"stan-hua/CytoImageNet","repo_kind":"official","path":"scripts/data_curation/clean_metadata.py","file_url":"https://github.com/stan-hua/CytoImageNet/blob/HEAD/scripts/data_curation/clean_metadata.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3f5f451d82f6b9c"}},{"code_sha256_prefix":"2efda2ebf2ec8122","entry":"get_data_paths","repo":"stan-hua/CytoImageNet","repo_kind":"official","path":"scripts/data_curation/clean_metadata.py","file_url":"https://github.com/stan-hua/CytoImageNet/blob/HEAD/scripts/data_curation/clean_metadata.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2efda2ebf2ec8122"}},{"code_sha256_prefix":"92b4394bc0094d47","entry":"get_labels","repo":"stan-hua/CytoImageNet","repo_kind":"official","path":"scripts/model_pretraining.py","file_url":"https://github.com/stan-hua/CytoImageNet/blob/HEAD/scripts/model_pretraining.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"92b4394bc0094d47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}