Masked diffusion transformer is a strong image synthesizer

• Main Authors: GAO, Shanghua, ZHOU, Pan, CHENG, Ming-Ming, YAN, Shuicheng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Training; Representation learning; Image synthesis; Computational modeling; Synthesizers; Source coding; Semantics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9024; https://ink.library.smu.edu.sg/context/sis_research/article/10027/viewcontent/2023_ICCV_MDT.pdf
• Institution: Singapore Management University

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this issue, we propose a Masked Diffusion Transformer (MDT) that introduces a mask latent modeling scheme to explicitly enhance the DPMs’ ability to contextual relation learning among object semantic parts in an image. During training, MDT operates in the latent space to mask certain tokens. Then, an asymmetric masking diffusion transformer is designed to predict masked tokens from unmasked ones while maintaining the diffusion generation process. Our MDT can reconstruct the full information of an image from its incomplete contextual input, thus enabling it to learn the associated relations among image tokens. Experimental results show that MDT achieves superior image synthesis performance, e.g., a new SOTA FID score in the ImageNet data set, and has about 3× faster learning speed than the previous SOTA DiT. The source code is released at https://github.com/sail-sg/MDT.