We look into Generative Adversarial Network (GAN), its prevalent variants and applications
in a number of sectors. GANs combine two neural networks that compete against one …

We introduce a new paradigm for generative modeling built on Continuous Normalizing
Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present …

Transformers have recently gained significant attention in the computer vision community.
However, the lack of scalability of self-attention mechanisms with respect to image size has …

Abstract Generative Adversarial Networks (GANs) can generate near photo realistic images
in narrow domains such as human faces. Yet, modeling complex distributions of datasets …

The advent of large-scale training has produced a cornucopia of powerful visual recognition
models. However, generative models, such as GANs, have traditionally been trained from …

With the development of web technology, multi-modal or multi-view data has surged as a
major stream for big data, where each modal/view encodes individual property of data …

Attention-based models, exemplified by the Transformer, can effectively model long range
dependency, but suffer from the quadratic complexity of self-attention operation, making …

Abstract Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces due to their
ability to scale to different resolutions. However, despite the success of deep learning-based …

We introduce a simple but effective unsupervised method for generating diverse images. We
train a class-conditional GAN model without using manually annotated class labels. Instead …

Datasets with missing values are very common in real world applications. GAIN, a recently
proposed deep generative model for missing data imputation, has been proved to …