Nothing Special   »   [go: up one dir, main page]
loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Niklas Penzel ; Gideon Stein and Joachim Denzler

Affiliation: Computer Vision Group, Friedrich Schiller University, Jena, Germany

Keyword(s): Debiasing, Change Penalization, Early Stopping, Fine-Tuning, Domain Adaptation.

Abstract: Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model. This behavior is especially problematic in critical areas such as autonomous driving or medical decision-making. In these scenarios, new data is often expensive and hard to come by. In this work, we present a method based on change penalization that takes a pre-trained model and adapts the weights to mitigate a previously detected bias. We achieve this by tuning a zero-initialized copy of a frozen pre-trained network. Our method needs very few, in extreme cases only a single, examples that contradict the bias to increase performance. Additionally, we propose an early stopping criterion to modify baselines and reduce overfitting. We evaluate our approach on a well-known bias in skin lesion classification and three other datasets from the domain shi ft literature. We find that our approach works especially well with very few images. Simple fine-tuning combined with our early stopping also leads to performance benefits for a larger number of tuning samples. (More)

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 65.254.225.175

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:
Penzel, N.; Stein, G. and Denzler, J. (2024). Reducing Bias in Pre-Trained Models by Tuning While Penalizing Change. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 90-101. DOI: 10.5220/0012345800003660

@conference{visapp24,
author={Niklas Penzel. and Gideon Stein. and Joachim Denzler.},
title={Reducing Bias in Pre-Trained Models by Tuning While Penalizing Change},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={90-101},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012345800003660},
isbn={978-989-758-679-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Reducing Bias in Pre-Trained Models by Tuning While Penalizing Change
SN - 978-989-758-679-8
IS - 2184-4321
AU - Penzel, N.
AU - Stein, G.
AU - Denzler, J.
PY - 2024
SP - 90
EP - 101
DO - 10.5220/0012345800003660
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

<style> #socialicons>a span { top: 0px; left: -100%; -webkit-transition: all 0.3s ease; -moz-transition: all 0.3s ease-in-out; -o-transition: all 0.3s ease-in-out; -ms-transition: all 0.3s ease-in-out; transition: all 0.3s ease-in-out;} #socialicons>ahover div{left: 0px;} </style>