Guided Diffusion from Self-Supervised Diffusion Features

TL;DR

This paper introduces a novel framework for extracting guidance directly from diffusion models, improving downstream task performance without relying on external classifiers or annotations.

Contribution

It proposes a method to derive guidance from diffusion models themselves, enhancing feature discriminability and sampling efficiency, with superior results on large-scale datasets.

Findings

Guidance from diffusion models matches class-conditioned models.

Feature regularization with Sinkhorn-Knopp improves discriminability.

Online training enables concurrent guidance extraction.

Abstract

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like DINO. However, recent studies have revealed that the feature representation derived from diffusion model itself is discriminative for numerous downstream tasks as well, which prompts us to propose a framework to extract guidance from, and specifically for, diffusion models. Our research has yielded several significant contributions. Firstly, the guidance signals from diffusion models are on par with those from class-conditioned diffusion models. Secondly, feature regularization, when based on the Sinkhorn-Knopp algorithm, can further enhance feature discriminability in comparison to unconditional diffusion models. Thirdly, we have constructed an online training approach that can concurrently derive guidance from diffusion models for diffusion models. Lastly, we have extended the application of diffusion models along the constant velocity path of ODE to achieve a more favorable balance between sampling steps and fidelity. The performance of our methods has been outstanding, outperforming related baseline comparisons in large-resolution datasets, such as ImageNet256, ImageNet256-100 and LSUN-Churches. Our code will be released.