Log In Sign Up

MOOD: Multi-level Out-of-distribution Detection

by   Ziqian Lin, et al.

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.


Layer Adaptive Deep Neural Networks for Out-of-distribution Detection

During the forward pass of Deep Neural Networks (DNNs), inputs gradually...

Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers

Detecting anomalous inputs, such as adversarial and out-of-distribution ...

Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble

Out-of-distribution (OOD) detection aims to discern outliers from the in...

Multi-Level Temporal Pyramid Network for Action Detection

Currently, one-stage frameworks have been widely applied for temporal ac...

A Statistical Difference Reduction Method for Escaping Backdoor Detection

Recent studies show that Deep Neural Networks (DNNs) are vulnerable to b...

DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors

In this paper, we propose a novel and highly practical score-level fusio...

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks

The problem of reducing processing time of large deep learning models is...