PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting

Zixin Guo, Tzu-Jui Julius Wang, Selen Pehlivan +2

Vision-language (VL) Pre-training (VLP) has shown to well generalize VL models over a wide range of VL downstream tasks, especially for cross-modal retrieval. However, it hinges on…