78 datasets found

Unsupervised anomaly detection with generative adversarial networks to guide marker discovery.

The proposed model is built on the theoretical analysis presented in [30,14]. Similar to the ARAE [14], our model provides flexibility in learning an autoencoder from the input...

OpenGAN: Open Set Generative Adversarial Networks

The dataset used in the paper is not explicitly described, but it is mentioned that it is a generative model dataset.

The dataset used in the paper is a 2D mixture of 8 Gaussians evenly arranged in a circle. The generator has to search for 2D submanifolds in a 3D space.

Brain MR and CT images of 24 patients that were scanned for radiotherapy treatment planning of brain tumors.

Generating accurate 3D models is a challenging problem that traditionally requires explicit learning from 3D datasets using supervised learning.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the CelebA-HQ, ImageNet, and Place2 datasets.

Generative adversarial nets (GANs) are a class of deep learning models that consist of two neural networks: a generator and a discriminator.

Generative adversarial networks (GANs) are powerful gen-erative models, but usually suffer from instability and generalization problem which may lead to poor generations.

The dataset used in this paper is a pseudo-random number generator (PRNG) dataset, which is a sequence of numbers that may not be distinguishable from a truly random sequence.

The SoloDance dataset contains 179 solo dance videos in real scenes collected online.

The iPER dataset was proposed by [25], which was collected in the laboratory environment.

Human Video Motion Transfer (HVMT) aims to, given an image of a source person, generate his/her video that imitates the motion of the driving person.

The dataset used in the paper is a 2D submanifold mixture of seven Gaussians arranged in a circle and embedded in 3D space.

The proposed framework generates JPEG compressed images using generative adversarial networks.

PresGANs prevent mode collapse and are amenable to predictive log-likelihood evaluation.

Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those...

Generative models have emerged as a promising technique for producing high-quality im-ages that are indistinguishable from real images.

Fashion image manipulation aims to generate high-resolution realistic fashion images with user-provided sketches and color strokes.