{"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/an-examination-of-the-robustness-of-reference","title":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","arxiv_id":"2305.14998","date":"2023-05-24","proceeding":null,"authors":["Saba Ahmadi","Aishwarya Agrawal"],"abstract":"Recently, reference-free metrics such as CLIPScore (Hessel et al., 2021), UMIC (Lee et al., 2021), and PAC-S (Sarto et al., 2023) have been proposed for automatic reference-free evaluation of image captions. Our focus lies in evaluating the robustness of these metrics in scenarios that require distinguishing between two captions with high lexical overlap but very different meanings. Our findings reveal that despite their high correlation with human judgments, CLIPScore, UMIC, and PAC-S struggle to identify fine-grained errors. While all metrics exhibit strong sensitivity to visual grounding errors, their sensitivity to caption implausibility errors is limited. Furthermore, we found that all metrics are sensitive to variations in the size of image-relevant objects mentioned in the caption, while CLIPScore and PAC-S are also sensitive to the number of mentions of image-relevant objects in the caption. Regarding linguistic aspects of a caption, all metrics show weak comprehension of negation, and CLIPScore and PAC-S are insensitive to the structure of the caption to a great extent. We hope our findings will guide further improvements in reference-free evaluation of image captioning.","url_abs":"https://arxiv.org/abs/2305.14998v2","url_pdf":"https://arxiv.org/pdf/2305.14998v2.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":"an-examination-of-the-robustness-of-reference","repo_url":"https://github.com/saba96/img-cap-metrics-robustness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"negation","task_name":"Negation"},{"task_slug":"sensitivity","task_name":"Sensitivity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.14998","atlas_url":"https://app.syntology.ai/?focus=2305.14998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14998"}},"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/saba96/img-cap-metrics-robustness","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"543a10a0d5688c1f","entry":"filter_yes_no","repo":"saba96/img-cap-metrics-robustness","repo_kind":"official","path":"negation/generate_negation_captions.py","file_url":"https://github.com/saba96/img-cap-metrics-robustness/blob/HEAD/negation/generate_negation_captions.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"543a10a0d5688c1f"}},{"code_sha256_prefix":"8b071d42bae109e6","entry":"load_vqa","repo":"saba96/img-cap-metrics-robustness","repo_kind":"official","path":"negation/generate_negation_captions.py","file_url":"https://github.com/saba96/img-cap-metrics-robustness/blob/HEAD/negation/generate_negation_captions.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8b071d42bae109e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}