Year: 2025
Type: article
Abstract: Ensuring the correctness of annotations in training datasets is one way to increase the trustworthiness and reliability of Machine Learning.This study aims to detect semantic shifts in datasets using Feature-Based Out-Of-Distribution and outlier detection methods, assuming Out-Of-Distribution samples are far from In-Distribution data.The experiments began with distance-based methods, such as k-Nearest Neighbours and Mahalanobis, followed by feature pyramids and dimensionality reduction techniques to address high-dimensional challenges.The results showed that the k-Nearest Neighbours detector performed robustly, achieving 100% AUROC when using ResNet50 on the Caltech-101 dataset, while the Mahalanobis detector showed unstable results with scores close to 50%.Moreover, selecting the right backbone model and feature levels, particularly low-level features from ResNet50, improved performance achieving AUROC score of 96% on the DelftBikes dataset for both k-Nearest Neighbours and Local Outlier Factor.The study highlights that k-Nearest Neighbours, Local Outlier Factor, alongside feature pyramids and dimensionality reduction constitute an effective setup for Out-of-Distribution detection, but optimal performance depends on tailored configurations across varying data conditions.
Source: Journal of WSCG
Authors: Susanne Wulz, Ulrich Krispel
Institutions: Graz University of Technology, Fraunhofer Austria
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4412765468