{"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/discriminability-objective-for-training","title":"Discriminability objective for training descriptive captions","arxiv_id":"1803.04376","date":"2018-03-12","proceeding":"CVPR 2018 6","authors":["Ruotian Luo","Brian Price","Scott Cohen","Gregory Shakhnarovich"],"abstract":"One property that remains lacking in image captions generated by contemporary\nmethods is discriminability: being able to tell two images apart given the\ncaption for one of them. We propose a way to improve this aspect of caption\ngeneration. By incorporating into the captioning training objective a loss\ncomponent directly related to ability (by a machine) to disambiguate\nimage/caption matches, we obtain systems that produce much more discriminative\ncaption, according to human evaluation. Remarkably, our approach leads to\nimprovement in other aspects of generated captions, reflected by a battery of\nstandard scores such as BLEU, SPICE etc. Our approach is modular and can be\napplied to a variety of model/loss combinations commonly proposed for image\ncaptioning.","url_abs":"http://arxiv.org/abs/1803.04376v2","url_pdf":"http://arxiv.org/pdf/1803.04376v2.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":"discriminability-objective-for-training","repo_url":"https://github.com/ruotianluo/DiscCaptioning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-captioning","task_name":"Image Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.04376","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}