no code implementations • 2 Jun 2022 • Sein Park, Junhyuk So, JunCheol Shin, Eunhyeok Park
The optimization of neural networks in terms of computation cost and memory footprint is crucial for their practical deployment on edge devices.
1 code implementation • NeurIPS 2021 • keunseo kim, JunCheol Shin, Heeyoung Kim
Several out-of-distribution (OOD) detection scores have been recently proposed for deep generative models because the direct use of the likelihood threshold for OOD detection has been shown to be problematic.