SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer

Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent breakthroughs have been driven by mask strategy that significantly improves the training efficiency of DiT with additional intra-image contextual learning.

Data and Resources

Cite this as

Rui Zhu, Yingwei Pan, Yehao Li, Ting Yao, Zhenglong Sun, Tao Mei, Chang Wen Chen (2024). Dataset: SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer. https://doi.org/10.57702/ibuwkskx

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Rui Zhu
More Authors
Yingwei Pan
Yehao Li
Ting Yao
Zhenglong Sun
Tao Mei
Chang Wen Chen