Activation Subspaces for Out-of-Distribution Detection

2025-08-29

AI Summary

This paper addresses the challenge of distinguishing in-distribution (ID) from out-of-distribution (OOD) samples in real-world deep learning deployments, with particular focus on both far-OOD and near-OOD scenarios. We propose an OOD detection method grounded in singular value decomposition (SVD) of the classification head’s weight matrix, which orthogonally decomposes deep-layer activations into two subspaces: a “dominant” subspace governing ID prediction and a “residual” subspace exhibiting higher discriminability for far-OOD inputs. By adaptively fusing confidence scores from both subspaces, our approach achieves shift-agnostic robustness without requiring auxiliary training or architectural modifications. Evaluated on standard benchmarks—including CIFAR and ImageNet—our method consistently outperforms state-of-the-art approaches, delivering substantial improvements in both far-OOD and near-OOD detection accuracy.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• Detecting out-of-distribution samples in deep learning models
• Distinguishing decisive versus insignificant activation components
• Improving OOD detection accuracy across distribution shift regimes

Innovation

• Singular value decomposition for activation analysis
• Decisive and insignificant components separation
• Combined subspace approach for OOD detection