GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methods

West non-West 11% 5% 66.8% 70.4% Diverse Scenarios in Different Regions Wedding Wedding Figure 1. Scenarios around the world including festivals and weddings. Even the same scenarios have distinct visual characteristics across regions (a.k.a. geographically diverse). Compared with prior Vision-Language Pre-trained Models (VLPs), GIVL achieves much better performance on non-Western data in GD-VCR [48]. GIVL can also make the gap between Western and non-Western cases much closer.