5 citations · 7 across the 6 of their papers we have counts for
8 papers
On the Feasibility and Generality of Patch-based Adversarial Attacks on Semantic Segmentation Problems
Soma Kontar, Andras Horvath
Deep neural networks were applied with success in a myriad of applications, but in safety critical use cases adversarial attacks still pose a significant threat. These attacks were…
Mitigating the Bias of Centered Objects in Common Datasets
Gergely Szabo, Andras Horvath
Convolutional networks are considered shift invariant, but it was demonstrated that their response may vary according to the exact location of the objects. In this paper we will de…
Receptive Field Size Optimization with Continuous Time Pooling
Dóra Babicz, Soma Kontár, Márk Pető +3
The pooling operation is a cornerstone element of convolutional neural networks. These elements generate receptive fields for neurons, in which local perturbations should have mini…
Filtered Batch Normalization
Andras Horvath, Jalal Al-afandi
It is a common assumption that the activation of different layers in neural networks follow Gaussian distribution. This distribution can be transformed using normalization techniqu…
MimosaNet: An Unrobust Neural Network Preventing Model Stealing
Kálmán Szentannai, Jalal Al-Afandi, András Horváth
Deep Neural Networks are robust to minor perturbations of the learned network parameters and their minor modifications do not change the overall network response significantly. Thi…
Application-level Studies of Cellular Neural Network-based Hardware Accelerators
Qiuwen Lou, Indranil Palit, Tang Li +3
As cost and performance benefits associated with Moore's Law scaling slow, researchers are studying alternative architectures (e.g., based on analog and/or spiking circuits) and/or…