POSTS
Similarities and Differences Between Out-of-Distribution (OOD) and Other Neighboring Problems
Most existing machine learning models are trained based on the closed-world assumption, where the test data is assumed to be drawn i.i.d. from the same distribution as the training data, known as in-distribution (ID). However, when models are deployed in an open-world scenario, test samples can be out-of-distribution (OOD) and therefore should be handled with caution. In addition to OOD detection, other problems also adopt the “open-world” assumption those are: outlier detection (OD), anomaly detection (AD), novelty detection (ND), and open set recognition (OSR).