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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Udayangani, Nimeshika, Dolatabadi, Hadi M., Erfani, Sarah, Leckie, Christopher
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918216026030080
author Udayangani, Nimeshika
Dolatabadi, Hadi M.
Erfani, Sarah
Leckie, Christopher
author_facet Udayangani, Nimeshika
Dolatabadi, Hadi M.
Erfani, Sarah
Leckie, Christopher
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16015
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection
Udayangani, Nimeshika
Dolatabadi, Hadi M.
Erfani, Sarah
Leckie, Christopher
Computer Vision and Pattern Recognition
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.
title Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.16015