MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
CoRR(2023)
摘要
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 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. We further improve MDT with a more efficient macro network
structure and training strategy, named MDTv2. Experimental results show that
MDTv2 achieves superior image synthesis performance, e.g., a new SOTA FID score
of 1.58 on the ImageNet dataset, and has more than 10x faster learning speed
than the previous SOTA DiT. The source code is released at
https://github.com/sail-sg/MDT.
更多查看译文
关键词
strong image synthesizer,diffusion
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要