Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/139218
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Hyperdimensional Feature Fusion for Out-of-Distribution Detection |
Author: | Wilson, S. Fischer, T. Sunderhauf, N. Dayoub, F. |
Citation: | Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), 2023, pp.2643-2653 |
Publisher: | IEEE |
Publisher Place: | Online |
Issue Date: | 2023 |
Series/Report no.: | IEEE Winter Conference on Applications of Computer Vision |
ISBN: | 9781665493468 |
ISSN: | 2472-6737 2642-9381 |
Conference Name: | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (3 Jan 2023 - 7 Jan 2023 : Waikoloa, Hawaii) |
Statement of Responsibility: | Samuel Wilson, Tobias Fischer, Niko Sünderhauf, Feras Dayoub |
Abstract: | We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection. In contrast to most existing works that perform OOD detection based on only a single layer of a neural network, we use similarity-preserving semi-orthogonal projection matrices to project the feature maps from multiple layers into a common vector space. By repeatedly applying the bundling operation ⊕, we create expressive class-specific descriptor vectors for all in-distribution classes. At test time, a simple and efficient cosine similarity calculation between descriptor vectors consistently identifies OOD samples with competitive performance to the current state-of-the-art whilst being significantly faster. We show that our method is orthogonal to recent state-of-the-art OOD detectors and can be combined with them to further improve upon the performance. |
Keywords: | Algorithms; Image recognition and understanding; object detection; categorization; segmentation |
Description: | Date Added to IEEE Xplore: 06 February 2023 |
Rights: | ©2023 IEEE |
DOI: | 10.1109/wacv56688.2023.00267 |
Grant ID: | http://purl.org/au-research/grants/arc/FL210100156 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/10030081/proceeding |
Appears in Collections: | Australian Institute for Machine Learning publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.