{"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/let-there-be-a-clock-on-the-beach-reducing","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","arxiv_id":"2110.01705","date":"2021-10-04","proceeding":null,"authors":["Ali Furkan Biten","Lluis Gomez","Dimosthenis Karatzas"],"abstract":"Explaining an image with missing or non-existent objects is known as object bias (hallucination) in image captioning. This behaviour is quite common in the state-of-the-art captioning models which is not desirable by humans. To decrease the object hallucination in captioning, we propose three simple yet efficient training augmentation method for sentences which requires no new training data or increase in the model size. By extensive analysis, we show that the proposed methods can significantly diminish our models' object bias on hallucination metrics. Moreover, we experimentally demonstrate that our methods decrease the dependency on the visual features. All of our code, configuration files and model weights will be made public.","url_abs":"https://arxiv.org/abs/2110.01705v2","url_pdf":"https://arxiv.org/pdf/2110.01705v2.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":"let-there-be-a-clock-on-the-beach-reducing","repo_url":"https://github.com/furkanbiten/object-bias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-hallucination","task_name":"Object Hallucination"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.01705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01705"}},"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/furkanbiten/object-bias","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"ee0eaa40d818b077","entry":"combine_coco_captions","repo":"furkanbiten/object-bias","repo_kind":"official","path":"chair/utils/chair.py","file_url":"https://github.com/furkanbiten/object-bias/blob/HEAD/chair/utils/chair.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee0eaa40d818b077"}},{"code_sha256_prefix":"d895aa09a553295e","entry":"combine_coco_instances","repo":"furkanbiten/object-bias","repo_kind":"official","path":"chair/utils/chair.py","file_url":"https://github.com/furkanbiten/object-bias/blob/HEAD/chair/utils/chair.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d895aa09a553295e"}},{"code_sha256_prefix":"46d214343afeec61","entry":"load_generated_captions","repo":"furkanbiten/object-bias","repo_kind":"official","path":"chair/utils/chair.py","file_url":"https://github.com/furkanbiten/object-bias/blob/HEAD/chair/utils/chair.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46d214343afeec61"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}