{"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/visualgpt-data-efficient-image-captioning-by","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","arxiv_id":"2102.10407","date":"2021-02-20","proceeding":"CVPR 2022 1","authors":["Jun Chen","Han Guo","Kai Yi","Boyang Li","Mohamed Elhoseiny"],"abstract":"The ability to quickly learn from a small quantity oftraining data widens the range of machine learning applications. In this paper, we propose a data-efficient image captioning model, VisualGPT, which leverages the linguistic knowledge from a large pretrained language model(LM). A crucial challenge is to balance between the use of visual information in the image and prior linguistic knowledge acquired from pretraining. We designed a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the pretrained LM as the language decoder ona small amount of in-domain training data. The proposed self-resurrecting activation unit produces sparse activations but has reduced susceptibility to zero gradients. We train the proposed model, VisualGPT, on 0.1%, 0.5% and 1% of MSCOCO and Conceptual Captions training data. Under these conditions, we outperform the best baseline model by up to 10.8% CIDEr on MS COCO and upto 5.4% CIDEr on Conceptual Captions. Further, Visual-GPT achieves the state-of-the-art result on IU X-ray, a medical report generation dataset. To the best of our knowledge, this is the first work that improves data efficiency of image captioning by utilizing LM pretrained on unimodal data. Our code is available at: https://github.com/Vision-CAIR/VisualGPT.","url_abs":"https://arxiv.org/abs/2102.10407v5","url_pdf":"https://arxiv.org/pdf/2102.10407v5.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":"visualgpt-data-efficient-image-captioning-by","repo_url":"https://github.com/Vision-CAIR/VisualGPT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"medical-report-generation","task_name":"Medical Report Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.10407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.10407"}},"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/Vision-CAIR/VisualGPT","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"d9dcfb510a5e2690","entry":"gelu","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"d9dcfb510a5e2690"}},{"code_sha256_prefix":"88e4fd969dc8b068","entry":"evaluate_loss","repo":"Vision-CAIR/VisualGPT","repo_kind":"official","path":"train_visualGPT.py","file_url":"https://github.com/Vision-CAIR/VisualGPT/blob/HEAD/train_visualGPT.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":"88e4fd969dc8b068"}},{"code_sha256_prefix":"1256a149181e6685","entry":"train_xe","repo":"Vision-CAIR/VisualGPT","repo_kind":"official","path":"train_visualGPT.py","file_url":"https://github.com/Vision-CAIR/VisualGPT/blob/HEAD/train_visualGPT.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":"1256a149181e6685"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}