denoising-diffusion-implicit-models

Papers using or citing this model 5

• Attention Is All You Need 197.2K citations · 2017 · arXiv

  The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention...

• U-Net: Convolutional Networks for Biomedical Image Segmentation 103.6K citations · 2015 · International Conference on Medical Image Computing and Computer-Assisted Intervention · arXiv

  There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the...

• Denoising Diffusion Probabilistic Models 36.5K citations · 2020 · arXiv (Cornell University) · arXiv

  We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a...

• Denoising Diffusion Implicit Models 14.2K citations · 2020 · International Conference on Learning Representations · arXiv

  Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present...

• Decoupled Weight Decay Regularization 2.8K citations · 2017 · arXiv.org · arXiv

  L$_2$ regularization and weight decay regularization are equivalent for standard stochastic gradient descent (when rescaled by the learning rate), but as we demonstrate this is \emph{not} the case for adaptive gradient algorithms, such...