Hyperdimensional Feature Fusion for Out-of-Distribution Detection

Samuel Wilson, Tobias Fischer, Niko Sünderhauf, Feras Dayoub; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 2644-2654


We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection. In contrast to many 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.

Related Material

[pdf] [supp]
@InProceedings{Wilson_2023_WACV, author = {Wilson, Samuel and Fischer, Tobias and S\"underhauf, Niko and Dayoub, Feras}, title = {Hyperdimensional Feature Fusion for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {2644-2654} }