{"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/compositional-generalization-in-image","title":"Compositional Generalization in Image Captioning","arxiv_id":"1909.04402","date":"2019-09-10","proceeding":"CONLL 2019 11","authors":["Mitja Nikolaus","Mostafa Abdou","Matthew Lamm","Rahul Aralikatte","Desmond Elliott"],"abstract":"Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts. We study the problem of compositional generalization, which measures how well a model composes unseen combinations of concepts when describing images. State-of-the-art image captioning models show poor generalization performance on this task. We propose a multi-task model to address the poor performance, that combines caption generation and image--sentence ranking, and uses a decoding mechanism that re-ranks the captions according their similarity to the image. This model is substantially better at generalizing to unseen combinations of concepts compared to state-of-the-art captioning models.","url_abs":"https://arxiv.org/abs/1909.04402v2","url_pdf":"https://arxiv.org/pdf/1909.04402v2.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":"compositional-generalization-in-image","repo_url":"https://github.com/mitjanikolaus/compositional-image-captioning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.04402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04402"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/mitjanikolaus/compositional-image-captioning","reach":null}],"summary":{"ran_honours":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"29bb920bd0979954","entry":"calc_average_for_pair","repo":"mitjanikolaus/compositional-image-captioning","repo_kind":"official","path":"plot_recall_results.py","file_url":"https://github.com/mitjanikolaus/compositional-image-captioning/blob/HEAD/plot_recall_results.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"29bb920bd0979954"}},{"code_sha256_prefix":"43ab196cba0414cc","entry":"check_args","repo":"mitjanikolaus/compositional-image-captioning","repo_kind":"official","path":"plot_recall_results.py","file_url":"https://github.com/mitjanikolaus/compositional-image-captioning/blob/HEAD/plot_recall_results.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"43ab196cba0414cc"}},{"code_sha256_prefix":"e27049b9e3cf1825","entry":"cosine_sim","repo":"mitjanikolaus/compositional-image-captioning","repo_kind":"official","path":"models/bottom_up_top_down_ranking.py","file_url":"https://github.com/mitjanikolaus/compositional-image-captioning/blob/HEAD/models/bottom_up_top_down_ranking.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e27049b9e3cf1825"}},{"code_sha256_prefix":"cb8446a797997e25","entry":"l2_norm","repo":"mitjanikolaus/compositional-image-captioning","repo_kind":"official","path":"models/bottom_up_top_down_ranking.py","file_url":"https://github.com/mitjanikolaus/compositional-image-captioning/blob/HEAD/models/bottom_up_top_down_ranking.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cb8446a797997e25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}