Out-of-distribution detection in 3D applications: a review

TL;DR

This review paper discusses the importance, methodologies, datasets, and evaluation metrics for out-of-distribution detection in 3D applications, emphasizing its role in developing trustworthy and robust AI systems.

Contribution

It provides a comprehensive overview of OOD detection techniques, datasets, and evaluation methods, highlighting future research directions in 3D vision and robustness.

Findings

Comparison of OOD detection methods and model structures

Introduction of benchmark datasets and evaluation metrics

Discussion of future research directions in 3D applications

Abstract

The ability to detect objects that are not prevalent in the training set is a critical capability in many 3D applications, including autonomous driving. Machine learning methods for object recognition often assume that all object categories encountered during inference belong to a closed set of classes present in the training data. This assumption limits generalization to the real world, as objects not seen during training may be misclassified or entirely ignored. As part of reliable AI, OOD detection identifies inputs that deviate significantly from the training distribution. This paper provides a comprehensive overview of OOD detection within the broader scope of trustworthy and uncertain AI. We begin with key use cases across diverse domains, introduce benchmark datasets spanning multiple modalities, and discuss evaluation metrics. Next, we present a comparative analysis of OOD detection methodologies, exploring model structures, uncertainty indicators, and distributional distance taxonomies, alongside uncertainty calibration techniques. Finally, we highlight promising research directions, including adversarially robust OOD detection and failure identification, particularly relevant to 3D applications. The paper offers both theoretical and practical insights into OOD detection, showcasing emerging research opportunities such as 3D vision integration. These insights help new researchers navigate the field more effectively, contributing to the development of reliable, safe, and robust AI systems.