RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection

The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings. In this paper, we observe that the singular value distributions of the in-distribution (ID) and OOD features are quite different: the OOD feature matrix tends to have a larger dominant singular value than the ID feature, and the class predictions of OOD samples are largely determined by it. This observation motivates us to propose \texttt{RankFeat}, a simple yet effective \texttt{post hoc} approach for OOD detection by removing the rank-1 matrix composed of the largest singular value and the associated singular vectors from the high-level feature (\emph{i.e.,} $\mathbf{X}{-} \mathbf{s}_{1}\mathbf{u}_{1}\mathbf{v}_{1}^{T}$). \texttt{RankFeat} achieves the \emph{state-of-the-art} performance and reduces the average false positive rate (FPR95) by 17.90\% compared with the previous best method. Extensive ablation studies and comprehensive theoretical analyses are presented to support the empirical results.