-
Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizer
This paper presents a high quality singing synthesizer that is able to model a voice with limited available recordings. Based on the sequence-to-sequence singing model, we... -
Creative Sketch Generation
Two datasets of creative sketches – Creative Birds and Creative Creatures – containing 10k sketches each along with part annotations. -
Image Reconstruction through Dynamic Scattering Media using Generative Advers...
A GAN network for reconstructing dynamic scattering images. -
MNIST and celebA
MNIST and celebA datasets were used to train and evaluate the proposed QDCGAN architecture. -
Automated Seed Quality Testing System using GAN & Active Learning
A dataset of 26K corn seed images, classified into pure seeds and three other defective classes (broken, silkcut, and discolored). -
Structurally aware bidirectional unpaired image to image translation between ...
Magnetic Resonance (MR) Imaging and Computed Tomography (CT) are the primary diagnostic imaging modalities quite frequently used for surgical planning and analysis. A general... -
GAN Training Dataset
The dataset used for training the generative adversarial network (GAN) model. -
GAN-EM: GAN based EM Learning Framework
GAN-EM: A GAN based EM Learning Framework for image clustering, semi-supervised classification and dimensionality reduction. -
Mixture of 25 2D-Gaussian Distributions
The dataset used in the Discriminator Rejection Sampling (DRS) algorithm, consisting of a mixture of 25 2D-Gaussian distributions. -
GAN Training Dynamics
The dataset used in this paper is a GAN training dataset, which is a non-convex game. -
This-city-does-not-exist Dataset
The dataset is used to test the generalization capabilities of the VQ-VAE 2 one-class classifier. -
Alps Dataset
The dataset is used to train and test the VQ-VAE 2 one-class classifier for detecting GAN manipulated multispectral satellite images. -
China and Scandinavian Season Transfer Datasets
The dataset is used to train and test the VQ-VAE 2 one-class classifier for detecting GAN manipulated multispectral satellite images. -
Land Cover (LC) Transfer Datasets
The dataset is used to train and test the VQ-VAE 2 one-class classifier for detecting GAN manipulated multispectral satellite images. -
Database in [28]
The database in [28] which was used to evaluate SEGAN in [14]. -
BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN
Human motion prediction model has applications in various fields of computer vision. Without taking into account the inherent stochasticity in the prediction of future pose... -
Dual-Attention GAN for Large-Pose Face Frontalization
Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. -
Generative Adversarial Active Learning
Generative Adversarial Active Learning (GAAL) algorithm using Generative Adversarial Networks (GAN) for active learning by query synthesis.