Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected …
Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. These methods do not make assumptions on the …
G Hinton - arXiv preprint arXiv:2212.13345, 2022 - arxiv.org
The aim of this paper is to introduce a new learning procedure for neural networks and to demonstrate that it works well enough on a few small problems to be worth further …
AC Li, M Prabhudesai, S Duggal… - Proceedings of the …, 2023 - openaccess.thecvf.com
The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a …
P Dhariwal, A Nichol - Advances in neural information …, 2021 - proceedings.neurips.cc
We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by …
Training deep neural networks requires gradient estimation from data batches to update parameters. Gradients per parameter are averaged over a set of data and this has been …
Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods …
Deep learning approaches to anomaly detection (AD) have recently improved the state of the art in detection performance on complex data sets, such as large collections of images or …
We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly …