Hyperdimensional Feature Fusion for Out-of-Distribution Detection

Simple item page
dc.contributor.authorWilson, S.
dc.contributor.authorFischer, T.
dc.contributor.authorSunderhauf, N.
dc.contributor.authorDayoub, F.
dc.contributor.conferenceIEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (3 Jan 2023 - 7 Jan 2023 : Waikoloa, Hawaii)
dc.date.issued2023
dc.descriptionDate Added to IEEE Xplore: 06 February 2023
dc.description.abstractWe 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.statementofresponsibilitySamuel Wilson, Tobias Fischer, Niko Sünderhauf, Feras Dayoub
dc.identifier.citationProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), 2023, pp.2643-2653
dc.identifier.doi10.1109/wacv56688.2023.00267
dc.identifier.isbn9781665493468
dc.identifier.issn2472-6737
dc.identifier.issn2642-9381
dc.identifier.orcidDayoub, F. [0000-0002-4234-7374]
dc.identifier.urihttps://hdl.handle.net/2440/139218
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeOnline
dc.relation.granthttp://purl.org/au-research/grants/arc/FL210100156
dc.relation.ispartofseriesIEEE Winter Conference on Applications of Computer Vision
dc.rights©2023 IEEE
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/10030081/proceeding
dc.subjectAlgorithms; Image recognition and understanding; object detection; categorization; segmentation
dc.titleHyperdimensional Feature Fusion for Out-of-Distribution Detection
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Australian Institute for Machine Learning publications