Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection
This addresses the need for reliable OOD detection in safety-critical applications, offering a novel approach that is incremental but challenges existing paradigms.
The paper tackles the problem of out-of-distribution (OOD) detection in deep learning by challenging the assumption that only penultimate-layer activations are informative, showing that intermediate layers also provide rich discriminative information. It proposes a training-free, model-agnostic method that aggregates features across multiple layers to form prototypes, improving AUROC by up to 4.41% and reducing FPR by 13.58% on benchmarks.
Deep learning models are increasingly deployed in safety-critical applications, where reliable out-of-distribution (OOD) detection is essential to ensure robustness. Existing methods predominantly rely on the penultimate-layer activations of neural networks, assuming they encapsulate the most informative in-distribution (ID) representations. In this work, we revisit this assumption to show that intermediate layers encode equally rich and discriminative information for OOD detection. Based on this observation, we propose a simple yet effective model-agnostic approach that leverages internal representations across multiple layers. Our scheme aggregates features from successive convolutional blocks, computes class-wise mean embeddings, and applies L_2 normalization to form compact ID prototypes capturing class semantics. During inference, cosine similarity between test features and these prototypes serves as an OOD score--ID samples exhibit strong affinity to at least one prototype, whereas OOD samples remain uniformly distant. Extensive experiments on state-of-the-art OOD benchmarks across diverse architectures demonstrate that our approach delivers robust, architecture-agnostic performance and strong generalization for image classification. Notably, it improves AUROC by up to 4.41% and reduces FPR by 13.58%, highlighting multi-layer feature aggregation as a powerful yet underexplored signal for OOD detection, challenging the dominance of penultimate-layer-based methods. Our code is available at: https://github.com/sgchr273/cosine-layers.git.