GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
This addresses the challenge of reliable OOD detection for image classification, offering incremental improvements with theoretical insights.
The paper tackles the problem of out-of-distribution detection in neural networks by introducing GradPCA, a method that uses PCA on gradient class-means based on NTK alignment, achieving more consistent performance across standard image classification benchmarks.
We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignment. GradPCA applies Principal Component Analysis (PCA) to gradient class-means, achieving more consistent performance than existing methods across standard image classification benchmarks. We provide a theoretical perspective on spectral OOD detection in neural networks to support GradPCA, highlighting feature-space properties that enable effective detection and naturally emerge from NTK alignment. Our analysis further reveals that feature quality -- particularly the use of pretrained versus non-pretrained representations -- plays a crucial role in determining which detectors will succeed. Extensive experiments validate the strong performance of GradPCA, and our theoretical framework offers guidance for designing more principled spectral OOD detectors.