{"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/radzero-similarity-based-cross-attention-for","title":"RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Radiology with Zero-Shot Multi-Task Capability","arxiv_id":"2504.07416","date":"2025-04-10","proceeding":null,"authors":["Jonggwon Park","Soobum Kim","Byungmu Yoon","Kyoyun Choi"],"abstract":"Recent advancements in multi-modal models have significantly improved vision-language alignment in radiology. However, existing approaches struggle to effectively utilize complex radiology reports for learning, rely on low-resolution images, and offer limited interpretability in attention mechanisms. To address these challenges, we introduce RadZero, a novel similarity-based cross-attention framework for vision-language alignment in radiology with zero-shot multi-task capability. RadZero leverages large language models to extract minimal semantic sentences from radiology reports and employs a multi-positive contrastive learning strategy to effectively capture relationships between images and multiple relevant textual descriptions. It also utilizes a pre-trained vision encoder with additional trainable Transformer layers, allowing efficient high-resolution image processing. By computing similarity between text embeddings and local image patch features, RadZero enables zero-shot inference with similarity probability for classification and pixel-level cross-modal similarity maps for grounding and segmentation. Experimental results on public chest radiograph benchmarks show that RadZero outperforms state-of-the-art methods in zero-shot classification, grounding, and segmentation. Furthermore, cross-modal similarity map analysis highlights its potential for improving explainability in vision-language alignment. Additionally, qualitative evaluation demonstrates RadZero's capability for open-vocabulary semantic segmentation, further validating its effectiveness in medical imaging.","url_abs":"https://arxiv.org/abs/2504.07416v1","url_pdf":"https://arxiv.org/pdf/2504.07416v1.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":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"open-vocabulary-semantic-segmentation-1","task_name":"Open-Vocabulary Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.07416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07416"}},"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/deepnoid-ai/RadZero","reach":null}],"summary":{"ran":2,"ran_fixture":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"bb9dd6ee6c82cee3","entry":"RadZeroLoss","repo":"deepnoid-ai/RadZero","repo_kind":"found_in_text","path":"exp/cxr_pt/model/losses.py","file_url":"https://github.com/deepnoid-ai/RadZero/blob/HEAD/exp/cxr_pt/model/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bb9dd6ee6c82cee3"}},{"code_sha256_prefix":"a884a79381e6a22f","entry":"SimilarityLogit","repo":"deepnoid-ai/RadZero","repo_kind":"found_in_text","path":"exp/cxr_pt/model/losses.py","file_url":"https://github.com/deepnoid-ai/RadZero/blob/HEAD/exp/cxr_pt/model/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a884a79381e6a22f"}},{"code_sha256_prefix":"1e839c65a035ce31","entry":"get_col_loss","repo":"deepnoid-ai/RadZero","repo_kind":"found_in_text","path":"exp/cxr_pt/model/losses.py","file_url":"https://github.com/deepnoid-ai/RadZero/blob/HEAD/exp/cxr_pt/model/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1e839c65a035ce31"}},{"code_sha256_prefix":"bbb84f36f311e83c","entry":"multi_positive_nce_loss","repo":"deepnoid-ai/RadZero","repo_kind":"found_in_text","path":"exp/cxr_pt/model/losses.py","file_url":"https://github.com/deepnoid-ai/RadZero/blob/HEAD/exp/cxr_pt/model/losses.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bbb84f36f311e83c"}},{"code_sha256_prefix":"992146da4994bef7","entry":"pad_and_gather","repo":"deepnoid-ai/RadZero","repo_kind":"found_in_text","path":"exp/cxr_pt/model/losses.py","file_url":"https://github.com/deepnoid-ai/RadZero/blob/HEAD/exp/cxr_pt/model/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"992146da4994bef7"}},{"code_sha256_prefix":"5e42d94071e7fc61","entry":"get_row_loss","repo":"deepnoid-ai/RadZero","repo_kind":"found_in_text","path":"exp/cxr_pt/model/losses.py","file_url":"https://github.com/deepnoid-ai/RadZero/blob/HEAD/exp/cxr_pt/model/losses.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":"5e42d94071e7fc61"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}