Výsledky vyhledávání - "Hurtik, Petr"

Report

Intersection over Union with smoothing for bounding box regression

Autor: Števuliáková, Petra, Hurtik, Petr

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 loss function smooth and continuous over the whole searched space, an

Externí odkaz: http://arxiv.org/abs/2303.15067

Zobrazit plný text záznamu

Report

Effective black box adversarial attack with handcrafted kernels

Autor: Dvořáček, Petr, Hurtik, Petr, Števuliáková, Petra

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 just one layer of handcrafted convolutional kernels and then train the

Externí odkaz: http://arxiv.org/abs/2303.13887

Zobrazit plný text záznamu

Report

Unproportional mosaicing

Autor: Molek, Vojtech, Hurtik, Petr, Vlasanek, Pavel, Adamczyk, David

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 samples, increasing data variability, and data space coverage. We prese

Externí odkaz: http://arxiv.org/abs/2303.02081

Zobrazit plný text záznamu

Report

Coastline extraction from ALOS-2 satellite SAR images

Autor: Hurtik, Petr, Vajgl, Marek

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-based imagery with synthetic aperture radar is used to provide the requir

Externí odkaz: http://arxiv.org/abs/2104.04722

Zobrazit plný text záznamu

Report

Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3

Autor: Hurtik, Petr, Molek, Vojtech, Hula, Jan, Vajgl, Marek, Vlasanek, Pavel, Nejezchleba, Tomas

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 of its weaknesses: a large amount of rewritten labels and inefficient

Externí odkaz: http://arxiv.org/abs/2005.13243

Zobrazit plný text záznamu