Hyperdimensional Feature Fusion for Out-Of-Distribution Detection
It addresses the problem of reliable OOD detection for AI safety, offering a novel method that improves over single-layer approaches.
The paper tackles Out-of-Distribution (OOD) detection by introducing Hyperdimensional Computing to fuse features from multiple neural network layers, achieving state-of-the-art performance with a simple cosine similarity test.
We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection. In contrast to most existing work that performs 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 $\oplus$, 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 better performance than the current state-of-the-art. We show that the hyperdimensional fusion of multiple network layers is critical to achieve best general performance.