{"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/tifa-accurate-and-interpretable-text-to-image","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","arxiv_id":"2303.11897","date":"2023-03-21","proceeding":"ICCV 2023 1","authors":["Yushi Hu","Benlin Liu","Jungo Kasai","Yizhong Wang","Mari Ostendorf","Ranjay Krishna","Noah A Smith"],"abstract":"Despite thousands of researchers, engineers, and artists actively working on improving text-to-image generation models, systems often fail to produce images that accurately align with the text inputs. We introduce TIFA (Text-to-Image Faithfulness evaluation with question Answering), an automatic evaluation metric that measures the faithfulness of a generated image to its text input via visual question answering (VQA). Specifically, given a text input, we automatically generate several question-answer pairs using a language model. We calculate image faithfulness by checking whether existing VQA models can answer these questions using the generated image. TIFA is a reference-free metric that allows for fine-grained and interpretable evaluations of generated images. TIFA also has better correlations with human judgments than existing metrics. Based on this approach, we introduce TIFA v1.0, a benchmark consisting of 4K diverse text inputs and 25K questions across 12 categories (object, counting, etc.). We present a comprehensive evaluation of existing text-to-image models using TIFA v1.0 and highlight the limitations and challenges of current models. For instance, we find that current text-to-image models, despite doing well on color and material, still struggle in counting, spatial relations, and composing multiple objects. We hope our benchmark will help carefully measure the research progress in text-to-image synthesis and provide valuable insights for further research.","url_abs":"https://arxiv.org/abs/2303.11897v3","url_pdf":"https://arxiv.org/pdf/2303.11897v3.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":"tifa-accurate-and-interpretable-text-to-image","repo_url":"https://github.com/Yushi-Hu/tifa","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"question-answering","task_name":"Question Answering"},{"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"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.11897","atlas_url":"https://app.syntology.ai/?focus=2303.11897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11897"}},"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/Yushi-Hu/tifa","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"6549f5f9e01f2568","entry":"tifa_score_single","repo":"Yushi-Hu/tifa","repo_kind":"official","path":"tifascore/tifa_score.py","file_url":"https://github.com/Yushi-Hu/tifa/blob/HEAD/tifascore/tifa_score.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6549f5f9e01f2568"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}