{"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/tise-a-toolbox-for-text-to-image-synthesis","title":"TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation","arxiv_id":"2112.01398","date":"2021-12-02","proceeding":null,"authors":["Tan M. Dinh","Rang Nguyen","Binh-Son Hua"],"abstract":"In this paper, we conduct a study on the state-of-the-art methods for text-to-image synthesis and propose a framework to evaluate these methods. We consider syntheses where an image contains a single or multiple objects. Our study outlines several issues in the current evaluation pipeline: (i) for image quality assessment, a commonly used metric, e.g., Inception Score (IS), is often either miscalibrated for the single-object case or misused for the multi-object case; (ii) for text relevance and object accuracy assessment, there is an overfitting phenomenon in the existing R-precision (RP) and Semantic Object Accuracy (SOA) metrics, respectively; (iii) for multi-object case, many vital factors for evaluation, e.g., object fidelity, positional alignment, counting alignment, are largely dismissed; (iv) the ranking of the methods based on current metrics is highly inconsistent with real images. To overcome these issues, we propose a combined set of existing and new metrics to systematically evaluate the methods. For existing metrics, we offer an improved version of IS named IS* by using temperature scaling to calibrate the confidence of the classifier used by IS; we also propose a solution to mitigate the overfitting issues of RP and SOA. For new metrics, we develop counting alignment, positional alignment, object-centric IS, and object-centric FID metrics for evaluating the multi-object case. We show that benchmarking with our bag of metrics results in a highly consistent ranking among existing methods that is well-aligned with human evaluation. As a by-product, we create AttnGAN++, a simple but strong baseline for the benchmark by stabilizing the training of AttnGAN using spectral normalization. We also release our toolbox, so-called TISE, for advocating fair and consistent evaluation of text-to-image models.","url_abs":"https://arxiv.org/abs/2112.01398v2","url_pdf":"https://arxiv.org/pdf/2112.01398v2.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":"tise-a-toolbox-for-text-to-image-synthesis","repo_url":"https://github.com/vinairesearch/tise-toolbox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.01398","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}