Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine
This addresses the need for reliable OOD detection in real-world ML deployments, offering an unsupervised approach that is incremental over prior label-dependent methods.
The paper tackled the problem of detecting out-of-distribution samples in machine learning systems by proposing an unsupervised energy-based detector using the Stiefel-Restricted Kernel Machine, which improved over existing energy-based detectors and deep generative models on standard datasets.
Detecting out-of-distribution (OOD) samples is an essential requirement for the deployment of machine learning systems in the real world. Until now, research on energy-based OOD detectors has focused on the softmax confidence score from a pre-trained neural network classifier with access to class labels. In contrast, we propose an unsupervised energy-based OOD detector leveraging the Stiefel-Restricted Kernel Machine (St-RKM). Training requires minimizing an objective function with an autoencoder loss term and the RKM energy where the interconnection matrix lies on the Stiefel manifold. Further, we outline multiple energy function definitions based on the RKM framework and discuss their utility. In the experiments on standard datasets, the proposed method improves over the existing energy-based OOD detectors and deep generative models. Through several ablation studies, we further illustrate the merit of each proposed energy function on the OOD detection performance.