Generative adversarial networks (GANs) have recently become a hot research topic;
however, they have been studied since 2014, and a large number of algorithms have been …

In this article, we review the literature on statistical theories of neural networks from three
perspectives: approximation, training dynamics, and generative models. In the first part …

We study the problem of learning conditional generators from noisy labeled samples, where
the labels are corrupted by random noise. A standard training of conditional GANs will not …

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic
forgetting even when they are trained to approximate a single target distribution. We show …

Inpainting methods aim to restore missing parts of corrupted images and play a critical role
in many computer vision applications, such as object removal and image restoration …

Detection transformers have recently shown promising object detection results and attracted
increasing attention. However, how to develop effective domain adaptation techniques to …

We introduce the Generalized Energy Based Model (GEBM) for generative modelling. These
models combine two trained components: a base distribution (generally an implicit model) …

Generative Adversarial Networks (GANs) are one of the most popular tools for learning
complex high dimensional distributions. However, generalization properties of GANs have …

Generative Adversarial Networks (GANs) are a type of generative model which have
received much attention due to their ability to model complex real-world data. Despite their …

Imitation learning trains a policy by mimicking expert demonstrations. Various imitation
methods were proposed and empirically evaluated, meanwhile, their theoretical …