Abstract
Background. Commonly, Deep Neural Networks (DNNs) generalize well on samples drawn from a distribution similar to that of the training set. However, DNNs' predictions are brittle and unreliable when the test samples are drawn from a dissimilar distribution. This is a major concern for deployment in real-world applications, where such behavior may come at a considerable cost, such as industrial production lines, autonomous vehicles, or healthcare applications. Contributions. We frame Out Of Distribution (OOD) detection in DNNs as a statistical hypothesis testing problem. Tests generated within our proposed framework combine evidence from the entire network. Unlike previous OOD detection heuristics, this framework returns a p-value for each test sample. It is guaranteed to maintain the Type I Error (T1E - incorrectly predicting OOD for an actual in-distribution sample) for test data. Moreover, this allows to combine several detectors while maintaining the T1E. Building on this framework, we suggest a novel OOD procedure based on low-order statistics. Our method achieves comparable or better results than state-of-the-art methods on well-accepted OOD benchmarks, without retraining the network parameters or assuming prior knowledge on the test distribution - and at a fraction of the computational cost.
Original language | English |
---|---|
Title of host publication | International Conference on Learning Representations |
Number of pages | 30 |
State | Published - 2022 |
Event | 10th International Conference on Learning Representations, ICLR 2022 - Virtual, Online Duration: 25 Apr 2022 → 29 Apr 2022 |
Conference
Conference | 10th International Conference on Learning Representations, ICLR 2022 |
---|---|
City | Virtual, Online |
Period | 25/04/22 → 29/04/22 |
All Science Journal Classification (ASJC) codes
- Education
- Language and Linguistics
- Computer Science Applications
- Linguistics and Language