Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/139218
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wilson, S. | - |
dc.contributor.author | Fischer, T. | - |
dc.contributor.author | Sunderhauf, N. | - |
dc.contributor.author | Dayoub, F. | - |
dc.date.issued | 2023 | - |
dc.identifier.citation | Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), 2023, pp.2643-2653 | - |
dc.identifier.isbn | 9781665493468 | - |
dc.identifier.issn | 2472-6737 | - |
dc.identifier.issn | 2642-9381 | - |
dc.identifier.uri | https://hdl.handle.net/2440/139218 | - |
dc.description | Date Added to IEEE Xplore: 06 February 2023 | - |
dc.description.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. | - |
dc.description.statementofresponsibility | Samuel Wilson, Tobias Fischer, Niko Sünderhauf, Feras Dayoub | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.relation.ispartofseries | IEEE Winter Conference on Applications of Computer Vision | - |
dc.rights | ©2023 IEEE | - |
dc.source.uri | https://ieeexplore.ieee.org/xpl/conhome/10030081/proceeding | - |
dc.subject | Algorithms; Image recognition and understanding; object detection; categorization; segmentation | - |
dc.title | Hyperdimensional Feature Fusion for Out-of-Distribution Detection | - |
dc.type | Conference paper | - |
dc.contributor.conference | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (3 Jan 2023 - 7 Jan 2023 : Waikoloa, Hawaii) | - |
dc.identifier.doi | 10.1109/wacv56688.2023.00267 | - |
dc.publisher.place | Online | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/FL210100156 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Dayoub, F. [0000-0002-4234-7374] | - |
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.