A pipeline for detecting and classifying objects in images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA21025BL" target="_blank" >RIV/61988987:17610/20:A21025BL - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9204121" target="_blank" >https://ieeexplore.ieee.org/document/9204121</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/DSMP47368.2020.9204121" target="_blank" >10.1109/DSMP47368.2020.9204121</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A pipeline for detecting and classifying objects in images

Popis výsledku v původním jazyce

With the increased accessibility to neural network frameworks and computation clouds, a wide range of competition websites offer real tasks for the neural network community to join. In this paper, we discuss a problem of object detection and classification. Based on our experience, we describe a general pipeline and necessary steps that may help researchers willing to participate in such competition. We partition the problem into two separate tasks. Firstly, we present state of the art for relevant neural networks concerning accuracy and computation time trade-off. Further, we create a survey of major techniques that leads to accuracy improvement. Namely, we recall image augmentation techniques, demonstrate the impact of various optimizers, and discuss ensemble techniques. The pipeline and techniques reflect our experience with a competition, in which we were able to reach a highly competitive solution and ended in fourth place. The uniqueness of our solution is that we used only free Google Colab computation service and still overperformed many more computation extensive approaches.

Název v anglickém jazyce

A pipeline for detecting and classifying objects in images

Popis výsledku anglicky

With the increased accessibility to neural network frameworks and computation clouds, a wide range of competition websites offer real tasks for the neural network community to join. In this paper, we discuss a problem of object detection and classification. Based on our experience, we describe a general pipeline and necessary steps that may help researchers willing to participate in such competition. We partition the problem into two separate tasks. Firstly, we present state of the art for relevant neural networks concerning accuracy and computation time trade-off. Further, we create a survey of major techniques that leads to accuracy improvement. Namely, we recall image augmentation techniques, demonstrate the impact of various optimizers, and discuss ensemble techniques. The pipeline and techniques reflect our experience with a competition, in which we were able to reach a highly competitive solution and ended in fourth place. The uniqueness of our solution is that we used only free Google Colab computation service and still overperformed many more computation extensive approaches.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

<a href="/cs/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centrum pro výzkum a vývoj metod umělé intelligence v automobilovém průmyslu regionu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of IEEE Third International Conference Data Stream Mining & Processing 2020

ISBN

978-1-7281-3214-3

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

163-168

Název nakladatele

IEEE

Místo vydání

—

Místo konání akce

Lvov, Ukrajina

Datum konání akce

21. 8. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—