Stone, RS, Ravikumar, N orcid.org/0000-0003-0134-107X, Bulpitt, AJ orcid.org/0000-0002-7905-4540 et al. (1 more author) (2022) Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 19-20 Jun 2022, New Orleans, LA, USA. IEEE , pp. 2897-2904. ISBN 978-1-6654-8740-5
Abstract
Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to mitigate. We argue the relevance of exploring methods which are completely ignorant of the presence of any bias, but are capable of identifying and mitigating them. Furthermore, we propose using Bayesian neural networks with an epistemic uncertainty-weighted loss function to dynamically identify potential bias in individual training samples and to weight them during training. We find a positive correlation between samples subject to bias and higher epistemic uncertainties. Finally, we show the method has potential to mitigate visual bias on a bias benchmark dataset and on a real-world face detection problem, and we consider the merits and weaknesses of our approach.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | ©2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Training , Visualization , Uncertainty , Correlation , Neural networks , Training data , Mathematical models |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 19 Apr 2023 08:36 |
Last Modified: | 19 Apr 2023 13:16 |
Published Version: | http://dx.doi.org/10.1109/cvprw56347.2022.00327 |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/cvprw56347.2022.00327 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:198160 |