{"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/room-for-improvement-in-automatic-image","title":"Room for improvement in automatic image description: an error analysis","arxiv_id":"1704.04198","date":"2017-04-13","proceeding":null,"authors":["Emiel van Miltenburg","Desmond Elliott"],"abstract":"In recent years we have seen rapid and significant progress in automatic\nimage description but what are the open problems in this area? Most work has\nbeen evaluated using text-based similarity metrics, which only indicate that\nthere have been improvements, without explaining what has improved. In this\npaper, we present a detailed error analysis of the descriptions generated by a\nstate-of-the-art attention-based model. Our analysis operates on two levels:\nfirst we check the descriptions for accuracy, and then we categorize the types\nof errors we observe in the inaccurate descriptions. We find only 20% of the\ndescriptions are free from errors, and surprisingly that 26% are unrelated to\nthe image. Finally, we manually correct the most frequently occurring error\ntypes (e.g. gender identification) to estimate the performance reward for\naddressing these errors, observing gains of 0.2--1 BLEU point per type.","url_abs":"http://arxiv.org/abs/1704.04198v1","url_pdf":"http://arxiv.org/pdf/1704.04198v1.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":"room-for-improvement-in-automatic-image","repo_url":"https://github.com/evanmiltenburg/ErrorAnalysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Image Description"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}