Recent Advances in OOD Detection: Problems and Approaches

2024-09-18

arXiv.org

AI Summary

The out-of-distribution (OOD) detection field lacks a systematic, scenario-aware taxonomy, hindering principled comparison and advancement. Method: We propose the first task-oriented, unified taxonomy—categorizing OOD methods into *training-driven*, *training-agnostic*, and *foundation-model-based* paradigms, grounded in problem scenarios and model access constraints; we formally establish foundation-model-enabled OOD detection as an independent paradigm and systematically survey its adaptation mechanisms, including test-time adaptation and multimodal extensions. Contribution/Results: Our work establishes an extensible classification framework, clarifies evaluation challenges and deployment bottlenecks, and releases a high-quality, curated literature repository on GitHub. This advances OOD detection from ad hoc method enumeration toward structured evolution and practical deployment.

Technology Category

• Machine Learning: Other Foundations of Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Out-of-distribution (OOD) detection aims to detect test samples outside the training category space, which is an essential component in building reliable machine learning systems. Existing reviews on OOD detection primarily focus on method taxonomy, surveying the field by categorizing various approaches. However, many recent works concentrate on non-traditional OOD detection scenarios, such as test-time adaptation, multi-modal data sources and other novel contexts. In this survey, we uniquely review recent advances in OOD detection from the problem scenario perspective for the first time. According to whether the training process is completely controlled, we divide OOD detection methods into training-driven and training-agnostic. Besides, considering the rapid development of pre-trained models, large pre-trained model-based OOD detection is also regarded as an important category and discussed separately. Furthermore, we provide a discussion of the evaluation scenarios, a variety of applications, and several future research directions. We believe this survey with new taxonomy will benefit the proposal of new methods and the expansion of more practical scenarios. A curated list of related papers is provided in the Github repository: https://github.com/shuolucs/Awesome-Out-Of-Distribution-Detection

Problem

• Detecting test samples outside training categories for reliable ML
• Surveying OOD detection from a task-oriented perspective
• Classifying methods as training-driven or training-agnostic

Innovation

• Task-oriented OOD detection survey
• Training-driven vs training-agnostic classification
• Large pre-trained model-based OOD detection