Keypoints selection using Evolutionary Algorithms

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA210268C" target="_blank" >RIV/61988987:17610/20:A210268C - isvavai.cz</a>
Result on the web
<a href="http://ceur-ws.org/Vol-2718/paper30.pdf" target="_blank" >http://ceur-ws.org/Vol-2718/paper30.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Keypoints selection using Evolutionary Algorithms
Original language description
This contribution presents the use of neural networks trained by an evolutionary algorithm for a selection of visual keypoints. Visual keypoints play an important role in many computer vision tasks but many algorithms for keypoint detection produce many keypoints which are not useful for the target task. We aim to filter them in a data-driven way. Our model uses a neural network that ranks each keypoint by a relevancy score that we use to choose top-K keypoints with the highest rank. These keypoints are then used for the target task, which is image classification in our case. Because we use discrete operations in our model, we can not easily obtain gradients for weight updates. We, therefore, optimize the weights of the network by CMA-ES algorithm, which enables efficient optimization of continuous parameters of black-box functions. In this article, we present our initial experiments with this method.
Czech name
—
Czech description
—

Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 20th Conference Information Technologies - Applications and Theory (ITAT 2020)
ISBN
—
ISSN
1613-0073
e-ISSN
—
Number of pages
6
Pages from-to
186-191
Publisher name
CEUR-WS
Place of publication
—
Event location
Oravská Lesná, Slovensko
Event date
Sep 18, 2020
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)