Papers of the day   All papers

Energy-based Out-of-distribution Detection

Comments

Sharon Y. Li: Suffering from overconfident softmax scores? Time to use energy scores! Excited to release our NeurIPS paper on "Energy-based Out-of-distribution Detection", a theoretically motivated framework for OOD detection. 1/n Paper: https://arxiv.org/abs/2010.03759 (w/ code included) https://t.co/OSwiJlcfPA

16 replies, 1468 likes


Yann LeCun: Energy-Based Models FTW.

2 replies, 386 likes


will grathwohl: hot shit alert 🔥

0 replies, 33 likes


Yanshuai Cao: Such a simple idea on such an old problem, I'm surprised nobody has tried this before ...

0 replies, 5 likes


Noel Codella, Ph.D.: A simple but effective approach for OOD detection. Being able to detect OOD data is critical for many applications. I hope to see more work in this space. #MachineLearning

0 replies, 3 likes


Content

Found on Oct 09 2020 at https://arxiv.org/pdf/2010.03759.pdf

PDF content of a computer science paper: Energy-based Out-of-distribution Detection