{"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/knowledge-enhanced-pre-training-for-auto","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","arxiv_id":"2302.14042","date":"2023-02-27","proceeding":null,"authors":["Xiaoman Zhang","Chaoyi Wu","Ya zhang","Yanfeng Wang","Weidi Xie"],"abstract":"While multi-modal foundation models pre-trained on large-scale data have been successful in natural language understanding and vision recognition, their use in medical domains is still limited due to the fine-grained nature of medical tasks and the high demand for domain knowledge. To address this challenge, we propose a novel approach called Knowledge-enhanced Auto Diagnosis (KAD) which leverages existing medical domain knowledge to guide vision-language pre-training using paired chest X-rays and radiology reports. We evaluate KAD on {four} external X-ray datasets and demonstrate that its zero-shot performance is not only comparable to that of fully-supervised models, but also superior to the average of three expert radiologists for three (out of five) pathologies with statistical significance. Moreover, when few-shot annotation is available, KAD outperforms all existing approaches in fine-tuning settings, demonstrating its potential for application in different clinical scenarios.","url_abs":"https://arxiv.org/abs/2302.14042v3","url_pdf":"https://arxiv.org/pdf/2302.14042v3.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":"knowledge-enhanced-pre-training-for-auto","repo_url":"https://github.com/xiaoman-zhang/kad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.14042","atlas_url":"https://app.syntology.ai/?focus=2302.14042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.14042"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/xiaoman-zhang/kad","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_honours":1,"ran_violates":3,"unverified":2},"by_repo_kind":{"listed":{"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":0,"samples":[{"code_sha256_prefix":"19e746da3aabc43e","entry":"get_gt","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A3_CLIP/plot_visualize_512.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A3_CLIP/plot_visualize_512.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":"19e746da3aabc43e"}},{"code_sha256_prefix":"9b2250a3d13ed688","entry":"get_sinusoid_encoding_table","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A3_CLIP/models/vit.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A3_CLIP/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"code_sha256_prefix":"f562860ea5f57aa0","entry":"get_text_features","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A3_CLIP/plot_visualize_512.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A3_CLIP/plot_visualize_512.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":"f562860ea5f57aa0"}},{"code_sha256_prefix":"7c29b374198bddcd","entry":"is_global_master","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A2_KEBERT/training/distributed.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A2_KEBERT/training/distributed.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c29b374198bddcd"}},{"code_sha256_prefix":"0377e309e95cfc3e","entry":"is_local_master","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A2_KEBERT/training/distributed.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A2_KEBERT/training/distributed.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0377e309e95cfc3e"}},{"code_sha256_prefix":"b092791002b40e8a","entry":"is_master","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A2_KEBERT/training/distributed.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A2_KEBERT/training/distributed.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b092791002b40e8a"}},{"code_sha256_prefix":"932d44bbf8bd0e3f","entry":"cosine_lr","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A2_KEBERT/training/scheduler.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A2_KEBERT/training/scheduler.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":"932d44bbf8bd0e3f"}},{"code_sha256_prefix":"ddcbd45e940484ee","entry":"gather_features","repo":"xiaoman-zhang/kad","repo_kind":"listed","path":"A3_CLIP/factory/loss.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A3_CLIP/factory/loss.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":"ddcbd45e940484ee"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}