Hongdong Li

Probing Diffusion Denoising Dynamics for Contrastive Representation Learning

Yasong Dai, Zeeshan Hayder, David Ahmedt-Aristizabal, Hongdong Li

Text-to-image diffusion models exhibit unprecedented generative capability and contain rich intermediate representations that can be useful for discriminative vision tasks. Motivated by this observation, we study a focused question: how can the denoising dynamics of a pretrained…Read more