Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific structural designs.

Data and Resources

Cite this as

Tao Yang, Cuiling Lan, Yan Lu, Nanning zheng (2024). Dataset: Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement. https://doi.org/10.57702/xwue9zz1

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2402.09712
Author Tao Yang
More Authors
Cuiling Lan
Yan Lu
Nanning zheng