loading
Papers

Research.Publish.Connect.

Paper

Authors: Bernardo Biesseck 1 ; Edson Araujo Junior 2 and Erickson Nascimento 2

Affiliations: 1 Universidade Federal de Minas Gerais (UFMG), Brazil, Instituto Federal de Mato Grosso (IFMT) and Brazil ; 2 Universidade Federal de Minas Gerais (UFMG) and Brazil

ISBN: 978-989-758-354-4

Keyword(s): Binary Tests, Keypoint Descriptor, Convolutional Neural Network.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Features Extraction ; Image and Video Analysis

Abstract: Convolutional Neural Networks (CNN) have been successfully used to recognize and extract visual patterns in different tasks such as object detection, object classification, scene recognition, and image retrieval. The CNNs have also contributed in local features extraction by learning local representations. A representative approach is LIFT that generates keypoint descriptors more discriminative than handcrafted algorithms like SIFT, BRIEF, and SURF. In this paper, we investigate the binary tests selection problem, and we present an in-depth study of the limit of searching solutions with CNNs when the gradient is computed from the local neighborhood of the selected pixels. We performed several experiments with a Siamese Network trained with corresponding and non-corresponding patch pairs. Our results show the presence of Local Minima and also a problem that we called Incorrect Gradient Components. We pursued to understand the binary tests selection problem and even some limitations of Convolutional Neural Networks to avoid searching for solutions in unviable directions. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.229.122.219

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Biesseck, B.; Araujo Jr., E. and Nascimento, E. (2019). Exploring the Limitations of the Convolutional Neural Networks on Binary Tests Selection for Local Features.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP, ISBN 978-989-758-354-4, pages 261-271. DOI: 10.5220/0007374102610271

@conference{visapp19,
author={Bernardo Janko Gon\c{C}alves Biesseck. and Araujo Jr., E. and Erickson R. Nascimento.},
title={Exploring the Limitations of the Convolutional Neural Networks on Binary Tests Selection for Local Features},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP,},
year={2019},
pages={261-271},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007374102610271},
isbn={978-989-758-354-4},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP,
TI - Exploring the Limitations of the Convolutional Neural Networks on Binary Tests Selection for Local Features
SN - 978-989-758-354-4
AU - Biesseck, B.
AU - Araujo Jr., E.
AU - Nascimento, E.
PY - 2019
SP - 261
EP - 271
DO - 10.5220/0007374102610271

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.