XOOD: A Self-supervised Algorithm for Detecting Out-of-Distribution Data for Image Classification
Document Type
Conference Proceeding
Publication Date
1-1-2026
Abstract
Neural Networks are known to be opaque in their decision-making process. In particular, it is known that, when encountering out-of-distribution (OOD) data, they can confidently provide an erroneous output without warning the user. It is well known that the “class probabilities” output by the softmax layer of a neural network are only weakly correlated with how confident the model should be about the prediction. Therefore, identifying out-of-distribution input data at inference time is critical for many applications of machine learning. We present XOOD: a self-supervised extreme value-based OOD detection framework for image classification. The algorithm relies 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 XOOD outperforms 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. The source code is available at https://github.com/MdSaifulIslamSajol/xood-icann/.
Publication Source (Journal or Book title)
Lecture Notes in Computer Science
First Page
521
Last Page
532
Recommended Citation
Berglind, F., Rajasekaran, M., Sajol, M., Temam, H., Mukhopadhyay, S., Das, K., Kumar, S., & Kallurupalli, K. (2026). XOOD: A Self-supervised Algorithm for Detecting Out-of-Distribution Data for Image Classification. Lecture Notes in Computer Science, 16068 LNCS, 521-532. https://doi.org/10.1007/978-3-032-04558-4_42