Revealing the Distributional Vulnerability of Discriminators by Implicit Generators Zhilin Zhao, Longbing Cao and Kun-Yu Lin. IEEE Transaction on Pattern Recognition and Machine Intelligence, 1-13, 2022. An explicit discriminator trained on observable in-distribution (ID) samples can make high-confidence prediction on out-of-distribution (OOD) samples due to its distributional vulnerability. This is primarily caused by the limited … Continue reading TPAMI: Non-IID/OOD – Distributional Vulnerability