{"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/mutual-information-divergence-a-unified","title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","arxiv_id":"2205.13445","date":"2022-05-25","proceeding":null,"authors":["Jin-Hwa Kim","Yunji Kim","Jiyoung Lee","Kang Min Yoo","Sang-Woo Lee"],"abstract":"Text-to-image generation and image captioning are recently emerged as a new experimental paradigm to assess machine intelligence. They predict continuous quantity accompanied by their sampling techniques in the generation, making evaluation complicated and intractable to get marginal distributions. Based on a recent trend that multimodal generative evaluations exploit a vison-and-language pre-trained model, we propose the negative Gaussian cross-mutual information using the CLIP features as a unified metric, coined by Mutual Information Divergence (MID). To validate, we extensively compare it with competing metrics using carefully-generated or human-annotated judgments in text-to-image generation and image captioning tasks. The proposed MID significantly outperforms the competitive methods by having consistency across benchmarks, sample parsimony, and robustness toward the exploited CLIP model. We look forward to seeing the underrepresented implications of the Gaussian cross-mutual information in multimodal representation learning and the future works based on this novel proposition.","url_abs":"https://arxiv.org/abs/2205.13445v1","url_pdf":"https://arxiv.org/pdf/2205.13445v1.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":"mutual-information-divergence-a-unified","repo_url":"https://github.com/naver-ai/mid.metric","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Hallucination Pair-wise Detection (1-ref)"},{"task_slug":null,"task_name":"Hallucination Pair-wise Detection (4-ref)"},{"task_slug":"human-judgment-classification","task_name":"Human Judgment Classification"},{"task_slug":"human-judgment-correlation","task_name":"Human Judgment Correlation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-judgment-classification-on-pascal-50s","task":"Human Judgment Classification","dataset":"Pascal-50S","model":"MID","rank_in_archive_order":1,"of":3,"metrics":{"Mean Accuracy":"85.2"},"uses_additional_data":false},{"leaderboard":"/sota/human-judgment-correlation-on-flickr8k-cf","task":"Human Judgment Correlation","dataset":"Flickr8k-CF","model":"MID","rank_in_archive_order":1,"of":3,"metrics":{"Kendall's Tau-b":"37.3"},"uses_additional_data":false},{"leaderboard":"/sota/human-judgment-correlation-on-flickr8k-expert","task":"Human Judgment Correlation","dataset":"Flickr8k-Expert","model":"MID","rank_in_archive_order":1,"of":4,"metrics":{"Kendall's Tau-c":"54.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.13445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13445"}},"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/naver-ai/mid.metric","reach":null}],"summary":{"ran_fixture":1,"ran_violates":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"22f6f48eaea48314","entry":"exp_smd","repo":"naver-ai/mid.metric","repo_kind":"official","path":"metrics/mid.py","file_url":"https://github.com/naver-ai/mid.metric/blob/HEAD/metrics/mid.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"22f6f48eaea48314"}},{"code_sha256_prefix":"ad5daf6a7e4f2ee2","entry":"log_det","repo":"naver-ai/mid.metric","repo_kind":"official","path":"metrics/mid.py","file_url":"https://github.com/naver-ai/mid.metric/blob/HEAD/metrics/mid.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad5daf6a7e4f2ee2"}},{"code_sha256_prefix":"cd5d20cde383de89","entry":"robust_inv","repo":"naver-ai/mid.metric","repo_kind":"official","path":"metrics/mid.py","file_url":"https://github.com/naver-ai/mid.metric/blob/HEAD/metrics/mid.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd5d20cde383de89"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}