Search Results for author: Peter Horvath

Found 4 papers, 1 papers with code

CNN architecture extraction on edge GPU

no code implementations24 Jan 2024 Peter Horvath, Lukasz Chmielewski, Leo Weissbart, Lejla Batina, Yuval Yarom

The results of the analysis show that neural network architectures are easily distinguishable using deep learning-based side-channel analysis.

Image Classification Side Channel Analysis +2

Surface Segmentation Using Implicit Divergence Constraint Between Adjacent Minimal Paths

no code implementations25 Nov 2021 Jozsef Molnar, Peter Horvath

We introduce a novel approach for object segmentation from 3D images using modified minimal path Eikonal equation.

Semantic Segmentation

An Elastic Energy Minimization Framework for Mean Surface Calculation

no code implementations31 Jul 2019 Jozsef Molnar, Peter Horvath

As the continuation of the contour mean calculation - designed for averaging the manual delineations of 3D layer stack images - in this paper, the most important equations: a) the reparameterization equations to determine the minimizing diffeomorphism and b) the proper centroid calculation for the surface mean calculation are presented.

Translation

modAL: A modular active learning framework for Python

2 code implementations2 May 2018 Tivadar Danka, Peter Horvath

modAL is a modular active learning framework for Python, aimed to make active learning research and practice simpler.

Active Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.