25 citations · 27 across the 6 of their papers we have counts for
7 papers
Virtual neural networks: hundreds of souls in a body
Petr Hurtik, Marek Vajgl, Zahra Alijani +1
A new concept, termed virtual neural networks, is introduced, where the count of trainable parameters is kept constant, and scalability is attained purely through computational res…
Toward Sub-1 kB Identity-Preserving Face Compression: A Benchmark of Codecs, a Custom Learned Codec, and Studies of Resolution, Demographic Fairness, Recompression, and Adversarial Robustness
Petr Hurtik, Jakub Sochor
Storing face images under a hard sub-kilobyte budget, as required for identity documents, smart-card biometrics and bandwidth-constrained verification, forces a codec to discard mo…
Intersection over Union with smoothing for bounding box regression
Petra Števuliáková, Petr Hurtik
We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the…
Effective black box adversarial attack with handcrafted kernels
Petr Dvořáček, Petr Hurtik, Petra Števuliáková
We propose a new, simple framework for crafting adversarial examples for black box attacks. The idea is to simulate the substitution model with a non-trainable model compounded of…
Unproportional mosaicing
Vojtech Molek, Petr Hurtik, Pavel Vlasanek +1
Data shift is a gap between data distribution used for training and data distribution encountered in the real-world. Data augmentations help narrow the gap by generating new data s…
Coastline extraction from ALOS-2 satellite SAR images
Petr Hurtik, Marek Vajgl
The continuous monitoring of a shore plays an essential role in designing strategies for shore protection against erosion. To avoid the effect of clouds and sunlight, satellite-bas…
Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3
Petr Hurtik, Vojtech Molek, Jan Hula +3
We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two…