AUPR-Out is similar to AUPR-In. All experiments were repeated five times with the random seed setting from 0 to 4. For SimCLR, We Other parameters are the same as the default settings. The learning rate and weight decay are set to 0.0003 and A.3 Stability of Training We track the relationship between loss and performance on the validation set for U The results are shown in Fig.( 1). Therefore, UOOD's training is not stable Relatively, their detection performance on unknown OOD samples is improved. Table 1: Performance of different methods on Known / Unknown OOD data set evaluated by AUROC.

In this paper, we study a setting called semi-supervised OOD detection.