A Cosine Similarity-based Method for Out-of-Distribution Detection

2023/06/23 by Nguyen Ngoc-Hieu, Ngoc-Hieu, Nguyen, Nguyen Hung-Quang +9 · 2 citations
Computer Science · #Anomaly Detection Techniques and Applications #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.2306.14920

openalex publication_date 2023/06/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The ability to detect OOD data is a crucial aspect of practical machine learning applications. In this work, we show that cosine similarity between the test feature and the typical ID feature is a good indicator of OOD data. We propose Class Typical Matching (CTM), a post hoc OOD detection algorithm that uses a cosine similarity scoring function. Extensive experiments on multiple benchmarks show that CTM outperforms existing post hoc OOD detection methods.

Cited by

• A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
• N2M: Bridging Navigation and Manipulation by Learning Pose Preference from Rollout

Related

• What If the Input is Expanded in OOD Detection?
• Large Class Separation is not what you need for Relational Reasoning-based OOD Detection
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
• Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data
• Out-of-Distribution Detection with Overlap Index