Baidu’s 10-Billion Scale ERNIE-ViLG Unified Generative Pretraining Framework Achieves SOTA Performance on Bidirectional Vision-Language Generation Tasks
Baidu researchers propose ERNIE-ViLG, a 10-billion parameter scale pretraining framework for bidirectional text-image generation. Pretrained on 145 million (Chinese) image-text pairs, ERNIE-ViLG achieves state-of-the-art performance on both text-to-image and image-to-text generation tasks.