Search Results for author: Vlad Taran

Found 3 papers, 1 papers with code

Batch Size Influence on Performance of Graphic and Tensor Processing Units during Training and Inference Phases

no code implementations31 Dec 2018 Yuriy Kochura, Yuri Gordienko, Vlad Taran, Nikita Gordienko, Alexandr Rokovyi, Oleg Alienin, Sergii Stirenko

The significant speedup was obtained even for extremely low-scale usage of Google TPUv2 units (8 cores only) in comparison to the quite powerful GPU NVIDIA Tesla K80 card with the speedup up to 10x for training stage (without taking into account the overheads) and speedup up to 2x for prediction stage (with and without taking into account overheads).

Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions

1 code implementation30 Dec 2018 Vlad Taran, Yuri Gordienko, Alexandr Rokovyi, Oleg Alienin, Sergii Stirenko

The obtained results demonstrated that for the most important classes the mean accuracy values of semantic image segmentation for coarse GT annotations are higher than for the fine GT ones, and the standard deviation values are vice versa.

Autonomous Driving Image Segmentation +3

Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images

no code implementations5 Jun 2018 Vlad Taran, Nikita Gordienko, Yuriy Kochura, Yuri Gordienko, Alexandr Rokovyi, Oleg Alienin, Sergii Stirenko

Here the results of application of several deep learning architectures (PSPNet and ICNet) for semantic image segmentation of traffic stereo-pair images are presented.

Image Segmentation Segmentation +2

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