1. Prompt Refinement with Image Pivot for Text-to-Image Generation
- Author
-
Zhan, Jingtao, Ai, Qingyao, Liu, Yiqun, Pan, Yingwei, Yao, Ting, Mao, Jiaxin, Ma, Shaoping, and Mei, Tao
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
For text-to-image generation, automatically refining user-provided natural language prompts into the keyword-enriched prompts favored by systems is essential for the user experience. Such a prompt refinement process is analogous to translating the prompt from "user languages" into "system languages". However, the scarcity of such parallel corpora makes it difficult to train a prompt refinement model. Inspired by zero-shot machine translation techniques, we introduce Prompt Refinement with Image Pivot (PRIP). PRIP innovatively uses the latent representation of a user-preferred image as an intermediary "pivot" between the user and system languages. It decomposes the refinement process into two data-rich tasks: inferring representations of user-preferred images from user languages and subsequently translating image representations into system languages. Thus, it can leverage abundant data for training. Extensive experiments show that PRIP substantially outperforms a wide range of baselines and effectively transfers to unseen systems in a zero-shot manner., Comment: Accepted by ACL 2024
- Published
- 2024