{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/speaking-the-same-language-matching-machine","title":"Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training","arxiv_id":"1703.10476","date":"2017-03-30","proceeding":"ICCV 2017 10","authors":["Rakshith Shetty","Marcus Rohrbach","Lisa Anne Hendricks","Mario Fritz","Bernt Schiele"],"abstract":"While strong progress has been made in image captioning over the last years,\nmachine and human captions are still quite distinct. A closer look reveals that\nthis is due to the deficiencies in the generated word distribution, vocabulary\nsize, and strong bias in the generators towards frequent captions. Furthermore,\nhumans -- rightfully so -- generate multiple, diverse captions, due to the\ninherent ambiguity in the captioning task which is not considered in today's\nsystems.\n  To address these challenges, we change the training objective of the caption\ngenerator from reproducing groundtruth captions to generating a set of captions\nthat is indistinguishable from human generated captions. Instead of\nhandcrafting such a learning target, we employ adversarial training in\ncombination with an approximate Gumbel sampler to implicitly match the\ngenerated distribution to the human one. While our method achieves comparable\nperformance to the state-of-the-art in terms of the correctness of the\ncaptions, we generate a set of diverse captions, that are significantly less\nbiased and match the word statistics better in several aspects.","url_abs":"http://arxiv.org/abs/1703.10476v2","url_pdf":"http://arxiv.org/pdf/1703.10476v2.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":"speaking-the-same-language-matching-machine","repo_url":"https://github.com/HemanthTejaY/Deep-Learning-Image-Captioning---A-comparitive-study","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"speaking-the-same-language-matching-machine","repo_url":"https://github.com/LisaAnne/Hallucination","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"speaking-the-same-language-matching-machine","repo_url":"https://github.com/rakshithShetty/captionGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"HemanthTejaY/Deep-Learning-Image-Captioning---A-comparitive-study","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"LisaAnne/Hallucination","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rakshithShetty/captionGAN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"beecc1a91bb62725e6bdea591c2ac70b153b1b7915fcb8510c438011fff78237","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}