Computer Vision Lab

Nikolay Falaleev

Deep Learning

» DeepLearning

Articles by category: DeepLearning


Mathematics Algorithms OpenCV Calibration Self-Driving Classification Segmentation Hardware Competitions ComputerVision
Title img
2023
27 Oct 2023

Deep Learning in Sports and Autonomous Vehicles

Deep Learning stack I am constantly asked about the role Deep Learning plays in sports performance tracking and analysis, so...

Title img
20 Jun 2023

Top-1 solution of SoccerNet Camera Calibration Challenge 2023

SoccerNet Camera Calibration Challenge 2023 Task This technical write-up describes some details of the winning submission to the SoccerNet Camera...

Title img
2022
30 Nov 2022

Four generations of Nvidia GPUs compared

Testing The post continues the series of benchmark rusults published previously with results for GPUs of the latest four generations...

Title img
2020
29 Jun 2020

Multi-task learning loss balancing

Multitask learning Multi-task artificial neural networks has several advantages over a set of single-task neural networks. Sharing of features between...

Title img
2018
06 Nov 2018

Benchmarking RTX 2080 Ti vs Pascal GPUs vs Tesla V100 with DL tasks

Testing The post presents results of Turing and Pascal GPUs benchmarking with a popular Deep Learning Benchmark. PyTorch based tests...

Title img
24 Oct 2018

Semantic Segmentation of Seismic Reflection Images

This post contains a description of the 14th place solution by Argus team (Ruslan Baikulov, Nikolay Falaleev) of the TGS...

Title img
23 Oct 2018

About Kaggle TGS Salt Identification Challenge

The goal The overall goal of the competition on Kaggle platform was to build an algorithm that automatically and accurately...

Title img
05 Jun 2018

Discussion of the Lyft Perception Challenge

Speedup tricks The basic prediction script was profiled with yappi multithreaded python profiler, and the profiling results gave rise to...

Title img
05 Jun 2018

Multiclass semantic segmentation with LinkNet34

Software and Hardware The model used in the submission as well as previous experiments were prepared with use of different...

Title img
31 May 2018

About Lyft Perception Challenge

The goal The overall goal of the Challenge is to generate a binary labeled image masks for vehicles and a...

Title img
21 Feb 2018

An approach to predicted class balancing

Postprocessing of predictions It was observed that the predicted class distribution in the Kaggle: IEEE’s Signal Processing Society - Camera...

Title img
20 Feb 2018

Camera model identification with deep learning

About the task The goal of the competition on Kaggle platform was to build an algorithm that identifies which camera...

Title img
2017
20 Oct 2017

How to run TensorFlow with CUDA 9 and cuDNN 7 in openSUSE on Ryzen

Introduction I was faced with the necessity of computational power increase in order to meet my needs in computer vision...

Title img
21 Sep 2017

Neural network for multiclass image segmentation

Introduction The main goal of the project is to train an fully convolutional neural network (encoder-decoder architecture with skip connections)...