UniD3: unified discrete diffusion for simultaneous vision-language generation

• Main Authors: Hu, Minghui, Zheng, Chuanxia, Cham, Tat-Jen, Suganthan, Ponnuthurai Nagaratnam, Yang, Zuopeng, Zheng, Heliang, Wang, Chaoyue, Tao, Dacheng
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; Diffusion; Computer Graphics
• Online Access: https://hdl.handle.net/10356/172665; https://openreview.net/forum?id=8JqINxA-2a
• Institution: Nanyang Technological University

The recently developed discrete diffusion model performs extraordinarily well in generation tasks, especially in the text-to-image task, showing great potential for modeling multimodal signals. In this paper, we leverage these properties and present a unified multimodal generation model, which can perform text-based, image-based, and even vision-language simultaneous generation using a single model. Specifically, we unify the discrete diffusion process for multimodal signals by proposing a unified Markov transition matrix and a unified objective. Moreover, we design a multimodal mutual attention module to highlight the inter-modal linkages, which is vital for multimodal generation. Extensive experiments indicate that our proposed method can perform comparably to the state-of-the-art solutions in various generation tasks.