Write and Paint: Generative Vision-Language Models are Unified Modal Learners

TL;DR

This paper introduces DaVinci, a unified vision-language generative model that learns to write and paint simultaneously, demonstrating strong performance across diverse tasks and establishing new benchmarks for multi-modal pre-training.

Contribution

The paper proposes a simple, scalable, and versatile unified model for vision-language generation, combining prefix language and image modeling for concurrent multi-modal learning.

Findings

DaVinci achieves competitive results on 27 tasks.

Unified pre-training enhances multi-modal capabilities.

Benchmarking reveals the effectiveness of self-supervised objectives.

Abstract

Recent advances in vision-language pre-training have pushed the state-of-the-art on various vision-language tasks, making machines more capable of multi-modal writing (image-to-text generation) and painting (text-to-image generation). However, few studies investigate if these two essential capabilities can be learned together and boost each other, making a versatile and powerful multi-modal foundation model. In this work, we disclose the potential of symmetric generative vision-language pre-training in learning to write and paint concurrently, and propose a new unified modal model, named DaVinci, trained with prefix language modeling and prefix image modeling, a simple generative self-supervised objective on image-text pairs. Thanks to the proposed prefix multi-modal modeling framework, DaVinci is simple to train, scalable to huge data, adaptable to both writing and painting tasks, and also strong on other vision, text, and multi-modal understanding tasks. DaVinci achieves competitive performance on a wide range of 27 generation/understanding tasks and demonstrates the superiority of combining vision/language generative pre-training. Furthermore, we carefully benchmark the performance of different vision-language pre-training objectives on different scales of pre-training datasets on a heterogeneous and broad distribution coverage. Our results demonstrate the potential of exploiting self-supervision in both language and vision inputs, and establish new, stronger baselines for future comparisons at different data scales. The code and pre-trained models are available at https://github.com/shizhediao/DaVinci.