mCLIP: Multilingual CLIP via Cross-lingual Transfer
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.- Anthology ID:
- 2023.acl-long.728
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13028–13043
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.728
- DOI:
- 10.18653/v1/2023.acl-long.728
- Cite (ACL):
- Guanhua Chen, Lu Hou, Yun Chen, Wenliang Dai, Lifeng Shang, Xin Jiang, Qun Liu, Jia Pan, and Wenping Wang. 2023. mCLIP: Multilingual CLIP via Cross-lingual Transfer. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13028–13043, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- mCLIP: Multilingual CLIP via Cross-lingual Transfer (Chen et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.acl-long.728.pdf