{"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-medical-multi-modal-contrastive","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","arxiv_id":"2403.10153","date":"2024-03-15","proceeding":null,"authors":["Yogesh Kumar","Pekka Marttinen"],"abstract":"We introduce eCLIP, an enhanced version of the CLIP model that integrates expert annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in contrastive multi-modal medical imaging analysis, notably data scarcity and the \"modality gap\" -- a significant disparity between image and text embeddings that diminishes the quality of representations and hampers cross-modal interoperability. eCLIP integrates a heatmap processor and leverages mixup augmentation to efficiently utilize the scarce expert annotations, thus boosting the model's learning effectiveness. eCLIP is designed to be generally applicable to any variant of CLIP without requiring any modifications of the core architecture. Through detailed evaluations across several tasks, including zero-shot inference, linear probing, cross-modal retrieval, and Retrieval Augmented Generation (RAG) of radiology reports using a frozen Large Language Model, eCLIP showcases consistent improvements in embedding quality. The outcomes reveal enhanced alignment and uniformity, affirming eCLIP's capability to harness high-quality annotations for enriched multi-modal analysis in the medical imaging domain.","url_abs":"https://arxiv.org/abs/2403.10153v3","url_pdf":"https://arxiv.org/pdf/2403.10153v3.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-medical-multi-modal-contrastive","repo_url":"https://github.com/ykumards/eclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"heatmap","method_name":"Heatmap"},{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.10153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10153"}},"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/ykumards/eclip","reach":null}],"summary":{"ran":3,"ran_draft_wrong":2,"unverified":7},"by_repo_kind":{"official":{"samples":12,"ran":5,"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":12,"samples":[{"code_sha256_prefix":"2d032fafc65b26df","entry":"ContrastiveLossOutput","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2d032fafc65b26df"}},{"code_sha256_prefix":"5e870e622f41b67b","entry":"ExpertMixupModule","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5e870e622f41b67b"}},{"code_sha256_prefix":"b343230215ea2775","entry":"_gather_embeddings_and_labels","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b343230215ea2775"}},{"code_sha256_prefix":"c734e1676e254908","entry":"get_rank","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c734e1676e254908"}},{"code_sha256_prefix":"76f570ae1d1022e5","entry":"sph_inter","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"76f570ae1d1022e5"}},{"code_sha256_prefix":"e98c6d1e9865f73f","entry":"BackpropType","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e98c6d1e9865f73f"}},{"code_sha256_prefix":"dfcfb3bb6f967137","entry":"ClipModule","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dfcfb3bb6f967137"}},{"code_sha256_prefix":"85bbc08066824740","entry":"ContrastiveLossWithTemperature","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"85bbc08066824740"}},{"code_sha256_prefix":"11142f3ccb491db4","entry":"ExpertClipModule","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"11142f3ccb491db4"}},{"code_sha256_prefix":"5c58c501e6e5cb78","entry":"GeodesicClipLoss","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5c58c501e6e5cb78"}},{"code_sha256_prefix":"4b7fdd1c6930c4d9","entry":"gather_features","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4b7fdd1c6930c4d9"}},{"code_sha256_prefix":"a6c4ca3acfd9ec02","entry":"gather_tensor","repo":"ykumards/eclip","repo_kind":"official","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a6c4ca3acfd9ec02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}