A Cosine Similarity-based Method for Out-of-Distribution Detection
This addresses the need for reliable OOD detection in practical ML applications, but it appears incremental as it builds on existing post hoc approaches.
The paper tackled the problem of detecting out-of-distribution (OOD) data in machine learning by proposing a method based on cosine similarity between test and in-distribution features, resulting in improved performance over existing post hoc methods as shown in experiments on multiple benchmarks.
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.