{"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/global-and-local-semantic-completion-learning","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","arxiv_id":"2306.07096","date":"2023-06-12","proceeding":null,"authors":["Rong-Cheng Tu","Yatai Ji","Jie Jiang","Weijie Kong","Chengfei Cai","Wenzhe Zhao","Hongfa Wang","Yujiu Yang","Wei Liu"],"abstract":"Cross-modal alignment plays a crucial role in vision-language pre-training (VLP) models, enabling them to capture meaningful associations across different modalities. For this purpose, numerous masked modeling tasks have been proposed for VLP to further promote cross-modal interactions. The core idea of previous masked modeling tasks is to focus on reconstructing the masked tokens based on visible context for learning local-local alignment. However, most of them pay little attention to the global semantic features generated for the masked data, resulting in a limited cross-modal alignment ability of global representations to local features of the other modality. Therefore, in this paper, we propose a novel Global and Local Semantic Completion Learning (GLSCL) task to facilitate global-local alignment and local-local alignment simultaneously. Specifically, the GLSCL task complements the missing semantics of masked data and recovers global and local features by cross-modal interactions. Our GLSCL consists of masked global semantic completion (MGSC) and masked local token completion (MLTC). MGSC promotes learning more representative global features, which have a great impact on the performance of downstream tasks, while MLTC reconstructs modal-fusion local tokens, further enhancing accurate comprehension of multimodal data. To evaluate the proposed approaches on cross-modal alignment, we develop a validation benchmark called ALIGN-BENCH. Moreover, we present a flexible vision encoder, enabling our model to simultaneously perform image-text and video-text multimodal tasks. Experimental results show that our proposed method obtains state-of-the-art performance on various vision-language benchmarks, such as visual question answering, image-text retrieval, and video-text retrieval.","url_abs":"https://arxiv.org/abs/2306.07096v2","url_pdf":"https://arxiv.org/pdf/2306.07096v2.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":"global-and-local-semantic-completion-learning","repo_url":"https://github.com/iigroup/scl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.07096","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}