{"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/more-grounded-image-captioning-by-distilling","title":"More Grounded Image Captioning by Distilling Image-Text Matching Model","arxiv_id":"2004.00390","date":"2020-04-01","proceeding":"CVPR 2020 6","authors":["Yuanen Zhou","Meng Wang","Daqing Liu","Zhenzhen Hu","Hanwang Zhang"],"abstract":"Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from satisfactory. To improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong supervision. To this end, we propose a Part-of-Speech (POS) enhanced image-text matching model (SCAN \\cite{lee2018stacked}): POS-SCAN, as the effective knowledge distillation for more grounded image captioning. The benefits are two-fold: 1) given a sentence and an image, POS-SCAN can ground the objects more accurately than SCAN; 2) POS-SCAN serves as a word-region alignment regularization for the captioner's visual attention module. By showing benchmark experimental results, we demonstrate that conventional image captioners equipped with POS-SCAN can significantly improve the grounding accuracy without strong supervision. Last but not the least, we explore the indispensable Self-Critical Sequence Training (SCST) \\cite{Rennie_2017_CVPR} in the context of grounded image captioning and show that the image-text matching score can serve as a reward for more grounded captioning \\footnote{https://github.com/YuanEZhou/Grounded-Image-Captioning}.","url_abs":"https://arxiv.org/abs/2004.00390v1","url_pdf":"https://arxiv.org/pdf/2004.00390v1.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":"more-grounded-image-captioning-by-distilling","repo_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-matching","task_name":"Text Matching"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00390"}},"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/YuanEZhou/Grounded-Image-Captioning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"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":"d2379d710eedc4ae","entry":"pack_wrapper","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"models/AttModel.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/models/AttModel.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2379d710eedc4ae"}},{"code_sha256_prefix":"bfac58a04b6835f5","entry":"pad_unsort_packed_sequence","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"models/AttModel.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/models/AttModel.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfac58a04b6835f5"}},{"code_sha256_prefix":"e56d2f9cbd9cb8b1","entry":"sort_pack_padded_sequence","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"models/AttModel.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/models/AttModel.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e56d2f9cbd9cb8b1"}},{"code_sha256_prefix":"0a4de8f498e3e70c","entry":"count_bad","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"eval_utils.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a4de8f498e3e70c"}},{"code_sha256_prefix":"45c05576f202e2b6","entry":"language_eval","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"eval_utils.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45c05576f202e2b6"}},{"code_sha256_prefix":"2b17380e9938d559","entry":"resnet18","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/misc/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b17380e9938d559"}},{"code_sha256_prefix":"d206d964368eeb24","entry":"resnet34","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/misc/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d206d964368eeb24"}},{"code_sha256_prefix":"fade30a7dab7a039","entry":"resnet50","repo":"YuanEZhou/Grounded-Image-Captioning","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/YuanEZhou/Grounded-Image-Captioning/blob/HEAD/misc/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fade30a7dab7a039"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}