Search Results for author:
Found 12 papers, 3 papers with code
Anomaly Detection with Adversarially Learned Perturbations of Latent Space
The Adversarial Distorter is a convolutional encoder that learns to produce effective perturbations and the autoencoder is a deep convolutional neural network that aims to reconstruct the images from the perturbed latent feature space.
Augment to Detect Anomalies with Continuous Labelling
Therefore, training a regressor on these augmented samples will result in more separable distributions of labels for normal and real anomalous data points.
Controlling Memorability of Face Images
In our proposed method, we first found a hyperplane in the latent space of StyleGAN to separate high and low memorable images.
The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning
Hence, we extensively investigate composition of temporal augmentations suitable for learning audiovisual representations; we find lossy spatio-temporal transformations that do not corrupt the temporal coherency of videos are the most effective.
CONTROLLING THE MEMORABILITY OF REAL AND UNREAL FACE IMAGES
In our proposed method, we first find a hyperplane in the latent space of StyleGAN to separate high and low memorable images.
OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection
In particular, context autoencoders have been successful in the novelty detection task because of the more effective representations they learn by reconstructing original images from randomly masked images.
Ranked #28 on
Anomaly Detection
on One-class CIFAR-10
Multi Scale Identity-Preserving Image-to-Image Translation Network for Low-Resolution Face Recognition
While they are capable of reconstructing images that are visually appealing, the identity-related information is not preserved.
CLAR: Contrastive Learning of Auditory Representations
We illustrate that by combining all these methods and with substantially less labeled data, our framework (CLAR) achieves significant improvement on prediction performance compared to supervised approach.
Latent Vector Recovery of Audio GANs
Through our deep neural network based method of training on real and synthesized audio, we are able to predict a latent vector that corresponds to a reasonable reconstruction of real audio.
Inverse mapping of face GANs
The vast majority of studies on latent vector recovery perform well only on generated images, we argue that our method can be used to determine a mapping between real human faces and latent-space vectors that contain most of the important face style details.
The Algonauts Project: A Platform for Communication between the Sciences of Biological and Artificial Intelligence
Recently, researchers of natural intelligence have begun using those AI models to explore how the brain performs such tasks.
Low Resolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecture
We propose a novel couple mappings method for low resolution face recognition using deep convolutional neural networks (DCNNs).
