Papers by Luoxiao Yang

Copied to clipboard

Challenge:	Existing Class Activation Mapping methods are ill-suited for interpreting non-autoregressive behaviors of diffusion-based architectures.
Approach:	They propose to use a method to generate parallel activation maps by probing intermediate representations in the transformer backbone to capture latent features and their class-specific gradients.
Outcome:	Experiments show that Diffusion-CAM significantly outperforms SoTA methods in localization accuracy and visual fidelity.