{"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/sparc-score-prompting-and-adaptive-fusion-for","title":"SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models","arxiv_id":"2502.16911","date":"2025-02-24","proceeding":"CVPR 2025 1","authors":["Kevin Miller","Samarth Mishra","Aditya Gangrade","Kate Saenko","Venkatesh Saligrama"],"abstract":"Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural adaptations, limiting zero-shot applicability. Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth. Using large language model insights on object co-occurrence, we introduce compound prompts grounded in realistic object combinations. Analysis of these prompt scores reveals VLM biases and ``AND''/``OR'' signal ambiguities, notably that maximum compound scores are surprisingly suboptimal compared to second-highest scores. We address these through a debiasing and score-fusion algorithm that corrects image bias and clarifies VLM response behaviors. Our method enhances other zero-shot approaches, consistently improving their results. Experiments show superior mean Average Precision (mAP) compared to methods requiring training data, achieved through refined object ranking for robust zero-shot MLR.","url_abs":"https://arxiv.org/abs/2502.16911v1","url_pdf":"https://arxiv.org/pdf/2502.16911v1.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":"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":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.16911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16911"}},"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/kjmillerCURIS/SPARC","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":5,"unverified":6},"by_repo_kind":{"found_in_text":{"samples":12,"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":12,"samples":[{"code_sha256_prefix":"f52b226226096fdd","entry":"average_precision","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f52b226226096fdd"}},{"code_sha256_prefix":"57eea7778536d6dc","entry":"calibrate_by_column","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"57eea7778536d6dc"}},{"code_sha256_prefix":"8f7c14445abd2d53","entry":"calibrate_by_row","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f7c14445abd2d53"}},{"code_sha256_prefix":"1ac7ca4edaf33ae2","entry":"calibrate_data","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ac7ca4edaf33ae2"}},{"code_sha256_prefix":"62b933388284c86f","entry":"depluralize","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"62b933388284c86f"}},{"code_sha256_prefix":"00a8953c48c8c5a7","entry":"stringmatch_to_compoundprompt","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00a8953c48c8c5a7"}},{"code_sha256_prefix":"a01340c62955961e","entry":"append_to_results","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.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":"a01340c62955961e"}},{"code_sha256_prefix":"a566c0956ff12a61","entry":"check_classname2compoundprompts","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.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":"a566c0956ff12a61"}},{"code_sha256_prefix":"7abb04913cf9225d","entry":"do_PCA_oneclass","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.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":"7abb04913cf9225d"}},{"code_sha256_prefix":"cdada95a46834fd6","entry":"load_data","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.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":"cdada95a46834fd6"}},{"code_sha256_prefix":"f48e8d0c29939aa2","entry":"predict_oneclass","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.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":"f48e8d0c29939aa2"}},{"code_sha256_prefix":"a376b8e3c7e8c520","entry":"run_SPARC","repo":"kjmillerCURIS/SPARC","repo_kind":"found_in_text","path":"run_SPARC.py","file_url":"https://github.com/kjmillerCURIS/SPARC/blob/HEAD/run_SPARC.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":"a376b8e3c7e8c520"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}