{"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/mclip-multilingual-clip-via-cross-lingual","title":"mCLIP: Multilingual CLIP via Cross-lingual Transfer","arxiv_id":null,"date":"2023-07-10","proceeding":"ACL 2023 7","authors":["Guanhua Chen","Lu Hou","Yun Chen","Wenliang Dai","Lifeng Shang","Xin Jiang","Qun Liu","Jia Pan","Wenping Wang"],"abstract":"Large-scale vision-language pretrained (VLP) models like CLIP have shown remarkable performance on various downstream cross-modal tasks. However, they are usually biased towards English due to the lack of sufficient non-English image-text pairs. Existing multilingual VLP methods often learn retrieval-inefficient single-stream models by translation-augmented non-English image-text pairs. In this paper, we introduce mCLIP, a retrieval-efficient dual-stream multilingual VLP model, trained by aligning the CLIP model and a Multilingual Text Encoder (MTE) through a novel Triangle Cross-modal Knowledge Distillation (TriKD) method. It is parameter-efficient as only two light projectors on the top of them are updated during distillation. Furthermore, to enhance the token- and sentence-level multilingual representation of the MTE, we propose to train it with machine translation and contrastive learning jointly before the TriKD to provide a better initialization. Empirical results show that mCLIP achieves new state-of-the-art performance for both zero-shot and finetuned multilingual image-text retrieval task.","url_abs":"https://aclanthology.org/2023.acl-long.728/","url_pdf":"https://aclanthology.org/2023.acl-long.728.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":"mclip-multilingual-clip-via-cross-lingual","repo_url":"https://github.com/ghchen18/acl23_mclip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"multilingual-cross-modal-retrieval","task_name":"multilingual cross-modal retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}