no code implementations • ICML Workshop INNF 2021 • Korbinian Abstreiter, Stefan Bauer, Arash Mehrjou
Score-based methods represented as stochastic differential equations on a continuous time domain have recently proven successful as a non-adversarial generative model.
no code implementations • 29 May 2021 • Korbinian Abstreiter, Sarthak Mittal, Stefan Bauer, Bernhard Schölkopf, Arash Mehrjou
In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective and thus encodes the information needed for denoising.