{"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/foundation-ark-accruing-and-reusing-knowledge","title":"Foundation Ark: Accruing and Reusing Knowledge for Superior and Robust Performance","arxiv_id":"2310.09507","date":"2023-10-14","proceeding":null,"authors":["Dongao Ma","Jiaxuan Pang","Michael B. Gotway","Jianming Liang"],"abstract":"Deep learning nowadays offers expert-level and sometimes even super-expert-level performance, but achieving such performance demands massive annotated data for training (e.g., Google's proprietary CXR Foundation Model (CXR-FM) was trained on 821,544 labeled and mostly private chest X-rays (CXRs)). Numerous datasets are publicly available in medical imaging but individually small and heterogeneous in expert labels. We envision a powerful and robust foundation model that can be trained by aggregating numerous small public datasets. To realize this vision, we have developed Ark, a framework that accrues and reuses knowledge from heterogeneous expert annotations in various datasets. As a proof of concept, we have trained two Ark models on 335,484 and 704,363 CXRs, respectively, by merging several datasets including ChestX-ray14, CheXpert, MIMIC-II, and VinDr-CXR, evaluated them on a wide range of imaging tasks covering both classification and segmentation via fine-tuning, linear-probing, and gender-bias analysis, and demonstrated our Ark's superior and robust performance over the SOTA fully/self-supervised baselines and Google's proprietary CXR-FM. This enhanced performance is attributed to our simple yet powerful observation that aggregating numerous public datasets diversifies patient populations and accrues knowledge from diverse experts, yielding unprecedented performance yet saving annotation cost. With all codes and pretrained models released at GitHub.com/JLiangLab/Ark, we hope that Ark exerts an important impact on open science, as accruing and reusing knowledge from expert annotations in public datasets can potentially surpass the performance of proprietary models trained on unusually large data, inspiring many more researchers worldwide to share codes and datasets to build open foundation models, accelerate open science, and democratize deep learning for medical imaging.","url_abs":"https://arxiv.org/abs/2310.09507v1","url_pdf":"https://arxiv.org/pdf/2310.09507v1.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":"foundation-ark-accruing-and-reusing-knowledge","repo_url":"https://github.com/jlianglab/ark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.09507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09507"}},"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/jlianglab/ark","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":8,"samples":[{"code_sha256_prefix":"de10fb5211d41960","entry":"build_omni_model","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_MICCAI2023/models.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_MICCAI2023/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"de10fb5211d41960"}},{"code_sha256_prefix":"a4fdd67606392a5b","entry":"build_omni_model_from_checkpoint","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_MICCAI2023/models.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_MICCAI2023/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a4fdd67606392a5b"}},{"code_sha256_prefix":"1e3ddd635c8fd366","entry":"build_transform_classification","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_MICCAI2023/dataloader.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_MICCAI2023/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1e3ddd635c8fd366"}},{"code_sha256_prefix":"f38860013e7a0c6c","entry":"get_config","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_MICCAI2023/utils.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_MICCAI2023/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f38860013e7a0c6c"}},{"code_sha256_prefix":"97ee7545105238e1","entry":"load_pretrained_weights","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_Plus/Finetuning/models.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_Plus/Finetuning/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"97ee7545105238e1"}},{"code_sha256_prefix":"7a93f39b9ebf9f84","entry":"metric_AUROC","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_MICCAI2023/utils.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_MICCAI2023/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7a93f39b9ebf9f84"}},{"code_sha256_prefix":"2e09f33e875638da","entry":"test_classification","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_MICCAI2023/trainer.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_MICCAI2023/trainer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2e09f33e875638da"}},{"code_sha256_prefix":"ace8378c28c1736c","entry":"vararg_callback_int","repo":"jlianglab/ark","repo_kind":"official","path":"Ark_MICCAI2023/utils.py","file_url":"https://github.com/jlianglab/ark/blob/HEAD/Ark_MICCAI2023/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ace8378c28c1736c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}