English

Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection

Computer Vision and Pattern Recognition 2025-11-25 v1

Abstract

Detecting out-of-distribution (OOD) data is essential for safe deployment of deep neural networks (DNNs). This problem becomes particularly challenging in the presence of long-tailed in-distribution (ID) datasets, often leading to high false positive rates (FPR) and low tail-class ID classification accuracy. In this paper, we demonstrate that exploiting inter-sample relationships using a graph-based representation can significantly improve OOD detection in long-tailed recognition of vision datasets. To this end, we use the feature space of a pre-trained model to initialize our graph structure. We account for the differences between the activation layer distribution of the pre-training vs. training data, and actively introduce Gaussianization to alleviate any deviations from a standard normal distribution in the activation layers of the pre-trained model. We then refine this initial graph representation using graph convolutional networks (GCNs) to arrive at a feature space suitable for long-tailed OOD detection. This leads us to address the inferior performance observed in ID tail-classes within existing OOD detection methods. Experiments over three benchmarks CIFAR10-LT, CIFAR100-LT, and ImageNet-LT demonstrate that our method outperforms the state-of-the-art approaches by a large margin in terms of FPR and tail-class ID classification accuracy.

Keywords

Cite

@article{arxiv.2511.16015,
  title  = {Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection},
  author = {Nimeshika Udayangani and Hadi M. Dolatabadi and Sarah Erfani and Christopher Leckie},
  journal= {arXiv preprint arXiv:2511.16015},
  year   = {2025}
}
R2 v1 2026-07-01T07:46:32.802Z