Hyperdimensional Feature Fusion for Out-of-Distribution Detection

Date

2023

Authors

Wilson, S.
Fischer, T.
Sunderhauf, N.
Dayoub, F.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), 2023, pp.2643-2653

Statement of Responsibility

Samuel Wilson, Tobias Fischer, Niko Sünderhauf, Feras Dayoub

Conference Name

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (3 Jan 2023 - 7 Jan 2023 : Waikoloa, Hawaii)

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.

School/Discipline

Dissertation Note

Provenance

Description

Date Added to IEEE Xplore: 06 February 2023

Access Status

Rights

©2023 IEEE

License

Call number

Persistent link to this record