Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation

Summary

This paper proposes a KPCA-based framework for out-of-distribution detection, learning a discriminative non-linear subspace from in-distribution features and using reconstruction error on that subspace to separate InD and OoD data. The authors select a Cosine-Gaussian kernel, motivated by two non-linear patterns linked to the InD-OoD disparity, and approximate it cheaply, with the approximation weighted by InD data confidence to scale to large datasets.