{"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/xgpt-cross-modal-generative-pre-training-for","title":"XGPT: Cross-modal Generative Pre-Training for Image Captioning","arxiv_id":"2003.01473","date":"2020-03-03","proceeding":null,"authors":["Qiaolin Xia","Haoyang Huang","Nan Duan","Dong-dong Zhang","Lei Ji","Zhifang Sui","Edward Cui","Taroon Bharti","Xin Liu","Ming Zhou"],"abstract":"While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new method of Cross-modal Generative Pre-Training for Image Captioning that is designed to pre-train text-to-image caption generators through three novel generation tasks, including Image-conditioned Masked Language Modeling (IMLM), Image-conditioned Denoising Autoencoding (IDA), and Text-conditioned Image Feature Generation (TIFG). As a result, the pre-trained XGPT can be fine-tuned without any task-specific architecture modifications to create state-of-the-art models for image captioning. Experiments show that XGPT obtains new state-of-the-art results on the benchmark datasets, including COCO Captions and Flickr30k Captions. We also use XGPT to generate new image captions as data augmentation for the image retrieval task and achieve significant improvement on all recall metrics.","url_abs":"https://arxiv.org/abs/2003.01473v2","url_pdf":"https://arxiv.org/pdf/2003.01473v2.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":[],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"xgpt","method_name":"XGPT"}],"datasets_introduced":[],"methods_introduced":[{"slug":"xgpt","name":"XGPT","full_name":"XGPT"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.01473","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}