1 code implementation • 4 Aug 2023 • Gergely Szabó, Paolo Bonaiuti, Andrea Ciliberto, András Horváth
To address this issue, we aimed to develop a new deep-learning based tracking method that relies solely on the assumption that cells can be tracked based on their spatio-temporal neighborhood, without restricting it to consecutive frames.
no code implementations • 29 May 2022 • Jalal Al-Afandi, Bálint Magyar, András Horváth
Data augmentation is a commonly applied technique with two seemingly related advantages.
no code implementations • 2 Nov 2020 • Dóra Babicz, Soma Kontár, Márk Pető, András Fülöp, Gergely Szabó, András Horváth
The pooling operation is a cornerstone element of convolutional neural networks.
no code implementations • 20 Jul 2020 • András Horváth
We present generalized versions of the commonly used maximum pooling operation: $k$th maximum and sorted pooling operations which selects the $k$th largest response in each pooling region, selecting locally consistent features of the input images.
no code implementations • 25 Sep 2019 • András Horváth
In this paper we will demonstrate that the approximation of the Wasserstein distance by sorting the samples is not always the optimal approach and the greedy assignment of the real and fake samples can result faster convergence and better approximation of the original distribution.
no code implementations • 2 Jul 2019 • 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.
no code implementations • 21 Feb 2019 • Botos Csaba, Adnane Boukhayma, Viveka Kulharia, András Horváth, Philip H. S. Torr
Standard adversarial training involves two agents, namely a generator and a discriminator, playing a mini-max game.