no code implementations • 20 Nov 2022 • Vahid Reza Khazaie, Anthony Wong, Mohammad Sabokrou
This paper establishes a novel evaluation framework for assessing the performance of out-of-distribution (OOD) detection in realistic settings.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 3 Jul 2022 • Vahid Reza Khazaie, Anthony Wong, John Taylor Jewell, Yalda Mohsenzadeh
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.
no code implementations • 3 Jul 2022 • Vahid Reza Khazaie, Anthony Wong, Yalda Mohsenzadeh
Therefore, training a regressor on these augmented samples will result in more separable distributions of labels for normal and real anomalous data points.
1 code implementation • 27 Mar 2021 • John Taylor Jewell, Vahid Reza Khazaie, Yalda Mohsenzadeh
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
1 code implementation • 23 Oct 2020 • Vahid Reza Khazaie, Nicky Bayat, Yalda Mohsenzadeh
While they are capable of reconstructing images that are visually appealing, the identity-related information is not preserved.
no code implementations • 16 Oct 2020 • Andrew Keyes, Nicky Bayat, Vahid Reza Khazaie, Yalda Mohsenzadeh
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.
1 code implementation • 11 Sep 2020 • Nicky Bayat, Vahid Reza Khazaie, Yalda Mohsenzadeh
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.