Wilson, S.Fischer, T.Sunderhauf, N.Dayoub, F.2023-08-212023-08-212023Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), 2023, pp.2643-265397816654934682472-67372642-9381https://hdl.handle.net/2440/139218Date Added to IEEE Xplore: 06 February 2023We 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.en©2023 IEEEAlgorithms; Image recognition and understanding; object detection; categorization; segmentationHyperdimensional Feature Fusion for Out-of-Distribution DetectionConference paper10.1109/wacv56688.2023.002672023-08-21599084Dayoub, F. [0000-0002-4234-7374]