Zhang, T., Wang, S., Bouaynaya, N. et al. (2 more authors) (2023) Out-of-distribution object detection through Bayesian uncertainty estimation. In: 2023 26th International Conference on Information Fusion Proceedings. 2023 26th International Conference on Information Fusion (FUSION 2023), 27-30 Jun 2023, Charleston, SC, USA. Institute of Electrical and Electronics Engineers (IEEE) ISBN 979-8-89034-485-4
Abstract
The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in many practical applications, out-of-distribution (OOD) instances are inevitable and usually lead to uncertainty in the results. In this paper, we propose a novel, intuitive, and scalable probabilistic object detection method for OOD detection. Unlike other uncertainty-modeling methods that either require huge computational costs to infer the weight distributions or rely on model training through synthetic outlier data, our method is able to distinguish between in-distribution (ID) data and OOD data via weight parameter sampling from proposed Gaussian distributions based on pre-trained networks. We demonstrate that our Bayesian object detector can achieve satisfactory OOD identification performance by reducing the FPR95 score by up to 8.19% and increasing the AUROC score by up to 13.94% when trained on BDD100k and VOC datasets as the ID datasets and evaluated on COCO2017 dataset as the OOD dataset.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 The Authors. Except as otherwise noted, this author-accepted version of a conference proceeding published in 2023 26th International Conference on Information Fusion (FUSION) is made available under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ |
Keywords: | Out-of-distribution detection; Uncertainty estimation; object detection; deep learning; image classification |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Sciences Research Council EP/T013265/1 ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL EP/V026747/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 14 Jun 2023 13:17 |
Last Modified: | 22 Nov 2023 11:57 |
Status: | Published |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Refereed: | Yes |
Identification Number: | 10.23919/FUSION52260.2023.10224150 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:200330 |