XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification
This addresses the critical need for reliable OOD detection in machine learning applications, offering significant performance improvements, though it is incremental as it builds on existing OOD detection approaches.
The paper tackles the problem of detecting out-of-distribution data in image classification by proposing XOOD, an extreme value-based framework with unsupervised and self-supervised algorithms, which reduces false-positive rate by 50% and improves inference time by an order of magnitude compared to state-of-the-art methods.
Detecting out-of-distribution (OOD) data at inference time is crucial for many applications of machine learning. We present XOOD: a novel extreme value-based OOD detection framework for image classification that consists of two algorithms. The first, XOOD-M, is completely unsupervised, while the second XOOD-L is self-supervised. Both algorithms rely on the signals captured by the extreme values of the data in the activation layers of the neural network in order to distinguish between in-distribution and OOD instances. We show experimentally that both XOOD-M and XOOD-L outperform state-of-the-art OOD detection methods on many benchmark data sets in both efficiency and accuracy, reducing false-positive rate (FPR95) by 50%, while improving the inferencing time by an order of magnitude.