Benchmarking evaluation demonstrates superior out-of-distribution detection across standard machine learning benchmarks, indicating cosine similarity effectively isolates novel inputs.
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.
No takes yet. Share an insight, caveat, or question.
Ngoc-Hieu et al. (2023) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: