Gradient-Based Novelty Detection Boosted by Self-Supervised Binary Classification


  • Jingbo Sun Arizona State University
  • Li Yang Arizona State University
  • Jiaxin Zhang Oak Ridge National Laboratory
  • Frank Liu Oak Ridge National Laboratory
  • Mahantesh Halappanavar Pacific Northwest National Laboratory
  • Deliang Fan Arizona State University
  • Yu Cao Arizona State University



Machine Learning (ML), Knowledge Representation And Reasoning (KRR), Reasoning Under Uncertainty (RU), Data Mining & Knowledge Management (DMKM)


Novelty detection aims to automatically identify out-of-distribution (OOD) data, without any prior knowledge of them. It is a critical step in data monitoring, behavior analysis and other applications, helping enable continual learning in the field. Conventional methods of OOD detection perform multi-variate analysis on an ensemble of data or features, and usually resort to the supervision with OOD data to improve the accuracy. In reality, such supervision is impractical as one cannot anticipate the anomalous data. In this paper, we propose a novel, self-supervised approach that does not rely on any pre-defined OOD data: (1) The new method evaluates the Mahalanobis distance of the gradients between the in-distribution and OOD data. (2) It is assisted by a self-supervised binary classifier to guide the label selection to generate the gradients, and maximize the Mahalanobis distance. In the evaluation with multiple datasets, such as CIFAR-10, CIFAR-100, SVHN and TinyImageNet, the proposed approach consistently outperforms state-of-the-art supervised and unsupervised methods in the area under the receiver operating characteristic (AUROC) and area under the precision-recall curve (AUPR) metrics. We further demonstrate that this detector is able to accurately learn one OOD class in continual learning.




How to Cite

Sun, J., Yang, L., Zhang, J., Liu, F., Halappanavar, M., Fan, D., & Cao, Y. (2022). Gradient-Based Novelty Detection Boosted by Self-Supervised Binary Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 8370-8377.



AAAI Technical Track on Machine Learning III