Activation Subspaces for Out-of-Distribution Detection

Abstract

To ensure the reliability of deep models in real-world applications, out-of-distribution (OOD) detection methods aim to distinguish samples close to the training distribution (in-distribution, ID) from those farther away (OOD). In this work, we propose a novel OOD detection method that utilizes singular value decomposition of the weight matrix of the classification head to decompose the model's activations into decisive and insignificant components, which contribute maximally, respectively minimally, to the final classifier output. We find that the subspace of insignificant components more effectively distinguishes ID from OOD data than raw activations in regimes of large distribution shifts (Far-OOD). This occurs because the classification objective leaves the insignificant subspace largely unaffected, yielding features that are ''untainted'' by the target classification task. Conversely, in regimes of smaller distribution shifts (Near-OOD), we find that activation shaping methods profit from only considering the decisive subspace, as the insignificant component can cause interference in the activation space. By combining two findings into a single approach, termed ActSub, we achieve state-of-the-art results in various standard OOD benchmarks.