-
2D submanifold mixture of Gaussians in 3D
The dataset used in the paper is a 2D submanifold mixture of seven Gaussians arranged in a circle and embedded in 3D space. -
Toward Joint Image Generation and Compression using Generative Adversarial Ne...
The proposed framework generates JPEG compressed images using generative adversarial networks. -
Prescribed Generative Adversarial Networks
PresGANs prevent mode collapse and are amenable to predictive log-likelihood evaluation. -
Speech enhancement generative adversarial network
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... -
A Bayesian Non-parametric Approach to Generative Models
Generative models have emerged as a promising technique for producing high-quality im-ages that are indistinguishable from real images. -
Fashion Editing Generative Adversarial Network (FE-GAN)
Fashion image manipulation aims to generate high-resolution realistic fashion images with user-provided sketches and color strokes. -
Synthetic dataset for FARGAN
The dataset used in the paper is a synthetic dataset for testing the proposed Fake-As-Real GAN (FARGAN) method. -
DCGAN dataset
Dataset used for training and testing the DCGAN model -
Disentangled Representation Learning
Disentangled representation learning endeavours to train a model proficient in disentangling the underlying factors of observed data. -
Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution
Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using... -
StyleGAN2-ADA Training Dataset
The dataset used for training the StyleGAN2-ADA algorithm consists of high-resolution spatial data. -
ShapeEditer: a StyleGAN Encoder for Face Swapping
Face swapping using StyleGAN -
Mixture of Gaussian tasks
The dataset used in the paper is a mixture of Gaussian tasks with 9 and 16 modes. -
Photo-Sketch Synthesis using Multi-Adversarial Networks
Photo-sketch synthesis using multi-adversarial networks -
Guided-GAN: Adversarial Representation Learning for Activity Recognition with...
Human activity recognition (HAR) is an important research field in ubiquitous computing where the acquisition of large-scale labeled sensor data is tedious, labor-intensive and... -
GANs for Anomaly Detection
Anomaly detection using GANs is an emerging research field. Anomaly detection using GANs is an emerging research field. Detecting and correctly classifying something unseen as... -
Vanderbilt University Medical Center Synthetic Derivative (CSD)
The dataset is a refined version of the SD dataset, which includes age, gender, ICD-9 codes, Current Procedural Terminology-Fourth Version (CPT-4) codes, body mass index (BMI),... -
Vanderbilt University Medical Center Synthetic Derivative (SD)
The dataset is a de-identified warehouse of over 2.2 million EHRs, which includes age, gender, ICD-9 codes, Current Procedural Terminology-Fourth Version (CPT-4) codes, body... -
Two-dimensional mixture of Gaussians
The dataset used in the paper is a two-dimensional mixture of Gaussians.
