55 citations · 94 across the 10 of their papers we have counts for
7 papers · 1 filter
Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping
Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh +1
Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a limi…
On Data Augmentation and Adversarial Risk: An Empirical Analysis
Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus +5
Data augmentation techniques have become standard practice in deep learning, as it has been shown to greatly improve the generalisation abilities of models. These techniques rely o…
The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification
Khaled Koutini, Hamid Eghbal-zadeh, Matthias Dorfer +1
Convolutional Neural Networks (CNNs) have had great success in many machine vision as well as machine audition tasks. Many image recognition network architectures have consequently…
On Conditioning GANs to Hierarchical Ontologies
Hamid Eghbal-zadeh, Lukas Fischer, Thomas Hoch
The recent success of Generative Adversarial Networks (GAN) is a result of their ability to generate high quality images from a latent vector space. An important application is the…
Mixture Density Generative Adversarial Networks
Hamid Eghbal-zadeh, Werner Zellinger, Gerhard Widmer
Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem. In this…
Probabilistic Generative Adversarial Networks
Hamid Eghbal-zadeh, Gerhard Widmer
We introduce the Probabilistic Generative Adversarial Network (PGAN), a new GAN variant based on a new kind of objective function. The central idea is to integrate a probabilistic…