Masked Diffusion as Self-supervised Representation Learner

arXiv:2308.05695v4 Announce Type: replace
Abstract: Denoising diffusion probabilistic models have recently demonstrated state-of-the-art generative performance and have been used as strong pixel-level representation learners. This paper decomposes the interrelation between the generative capability and representation learning ability inherent in diffusion models. We present the masked diffusion model (MDM), a scalable self-supervised representation learner for semantic segmentation, substituting the conventional additive Gaussian noise of traditional diffusion with a masking mechanism. Our proposed approach convincingly surpasses prior benchmarks, demonstrating remarkable advancements in …

abstract art arxiv capability cs.cv denoising diffusion diffusion model diffusion models generative mdm paper performance pixel representation representation learning scalable state type