MOOD: Multi-level Out-of-distribution Detection

Abstract

Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from causing a model to fail during deployment. While improved OOD detection methods have emerged, they often rely on the final layer outputs and require a full feedforward pass for any given input. In this paper, we propose a novel framework, multi-level out-of-distribution detection MOOD, which exploits intermediate classifier outputs for dynamic and efficient OOD inference. We explore and establish a direct relationship between the OOD data complexity and optimal exit level, and show that easy OOD examples can be effectively detected early without propagating to deeper layers. At each exit, the OOD examples can be distinguished through our proposed adjusted energy score, which is both empirically and theoretically suitable for networks with multiple classifiers. We extensively evaluate MOOD across 10 OOD datasets spanning a wide range of complexities. Experiments demonstrate that MOOD achieves up to 71.05% computational reduction in inference, while maintaining competitive OOD detection performance.

arXiv comment12 pages, 8 figures, CVPR2021

References in corpus (11)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Adaptive Computation Time for Recurrent Neural Networks
• TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
• Multi-Scale Dense Networks for Resource Efficient Image Classification
• Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
• Pixel-wise Attentional Gating for Parsimonious Pixel Labeling
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output