Rethinking Conditional Diffusion Sampling with Progressive Guidance
Dec 10, 2023
Speakers
Anh-Dung Dinh
Speaker · 0 followers
Daochang Liu
Speaker · 0 followers
About
This paper tackles two critical challenges encountered in classifier guidance for diffusion generative models, i.e., the lack of diversity and the presence of adversarial effects. These issues often result in a scarcity of diverse samples or the generation of non-robust features. The underlying cause lies in the mechanism of classifier guidance, where discriminative gradients push samples to be recognized as conditions aggressively. This inadvertently suppresses information with common features among relevant classes, resulting in a limited pool of features with less diversity or the absence of robust features for image construction.We propose a generalized classifier guidance method called Progressive Guidance, which mitigates the problems by allowing relevant classes' gradients to contribute to shared information construction when the image is noisy in early sampling steps. In the later sampling stage, we progressively enhance gradients to refine the details in the image toward the primary condition. This helps to attain a high level of diversity and robustness compared to the vanilla classifier guidance. Experimental results demonstrate that our proposed method further improves the image quality while offering a significant level of diversity as well as robust features.This paper tackles two critical challenges encountered in classifier guidance for diffusion generative models, i.e., the lack of diversity and the presence of adversarial effects. These issues often result in a scarcity of diverse samples or the generation of non-robust features. The underlying cause lies in the mechanism of classifier guidance, where discriminative gradients push samples to be recognized as conditions aggressively. This inadvertently suppresses information with common features…
Organizer
NeurIPS 2023
Account · 648 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Optimistic Rates for Multi-Task Representation Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Faster Query Times for Fully Dynamic k-Center Clustering with Outliers
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Practical Contextual Bandits with Feedback Graphs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Optimistic Meta-Gradients
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions
Watch later
Yuseung Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Robust Statistics for Simulation-based Inference under Model Misspecification
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%