Paper ID: 2306.14920
A Cosine Similarity-based Method for Out-of-Distribution Detection
Nguyen Ngoc-Hieu, Nguyen Hung-Quang, The-Anh Ta, Thanh Nguyen-Tang, Khoa D Doan, Hoang Thanh-Tung
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.
Submitted: Jun 23, 2023