loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock
The Necessity and Pitfall of Augmentation in Deep Learning: Observations During a Case Study in Triplet Learning for Coin Images

Topics: Advanced Learning Methods; Classification and Clustering; Deep Learning and Neural Networks; Feature Selection and Extraction; Image and Video Analysis and Understanding; Industry Related Applications; Machine Learning Methods

Author: Daniel Soukup

Affiliation: AIT Austrian Institute of Technology GmbH, Center for Vision, Automation & Control, Vienna, Austria

Keyword(s): Deep Embedding Learning, Triplet Learning, Augmentation, Interpolation, Novelty-aware Classification.

Abstract: We conducted a case study on a subset of the MUSCLE CIS image benchmark of modern coins with the goal to assess the potential of deep embedding learning for generating representative CNN feature vectors of coin images, which are clustered class by class. In the course of training our models (CNN), we applied algorithmic rotational augmentation to the coin images to enforce rotational invariance. While augmentation is a usual procedure for regularizing deep learning models towards more geometric invariance, exactly that procedure revealed an interesting yet precarious pitfall in deep embedding learning: its susceptibility to interpolation errors. That interpolation bias results in distorted and ambiguous representation clusters of coin classes in the feature space, jeopardizing classification capabilities.

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 18.119.131.72

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:
Soukup, D. (2020). The Necessity and Pitfall of Augmentation in Deep Learning: Observations During a Case Study in Triplet Learning for Coin Images. In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-397-1; ISSN 2184-4313, SciTePress, pages 387-394. DOI: 10.5220/0008910303870394

@conference{icpram20,
author={Daniel Soukup.},
title={The Necessity and Pitfall of Augmentation in Deep Learning: Observations During a Case Study in Triplet Learning for Coin Images},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2020},
pages={387-394},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008910303870394},
isbn={978-989-758-397-1},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - The Necessity and Pitfall of Augmentation in Deep Learning: Observations During a Case Study in Triplet Learning for Coin Images
SN - 978-989-758-397-1
IS - 2184-4313
AU - Soukup, D.
PY - 2020
SP - 387
EP - 394
DO - 10.5220/0008910303870394
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic