Abstract
Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaining decent performance on downstream tasks. However, current WVLP methods use only local descriptions of images, i.e., object tags, as cross-modal anchors to construct weakly-aligned image-text pairs for pre-training. This affects the data quality and thus the effectiveness of pre-training. In this paper, we propose to directly take a small number of aligned image-text pairs as anchors, and represent each unaligned image and text by its similarities to these anchors, i.e., relative representations. We build a WVLP framework based on the relative representations, namely RELIT, which collects high-quality weakly-aligned image-text pairs from large-scale image-only and text-only data for pre-training through relative representation-based retrieval and generation. Experiments on four downstream tasks show that RELIT achieves new state-of-the-art results under the weakly supervised setting.- Anthology ID:
- 2023.acl-long.464
- 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:
- 8341–8355
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.464
- DOI:
- 10.18653/v1/2023.acl-long.464
- Cite (ACL):
- Chi Chen, Peng Li, Maosong Sun, and Yang Liu. 2023. Weakly Supervised Vision-and-Language Pre-training with Relative Representations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8341–8355, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Weakly Supervised Vision-and-Language Pre-training with Relative Representations (Chen et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.acl-long.464.pdf