The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
Out-of-distribution (OOD) detection is essential for model trustworthiness which aims to sensitively identify semantic OOD samples and robustly generalize for covariate-shifted OOD samples. However, we discover that the superior OOD detection performance of state-of-the-art methods is achieved by secretly sacrificing the OOD generalization ability. Specifically, the classification accuracy of these …