Energy-based Out-of-distribution Detection

By Weitang Liu, Xiaoyun Wang, John Douglas Owens, Yixuan Li. 2020

2,043 citations recorded by the source corpus.

Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density of the inputs and are less susceptible to the overconfidence issue. Within this framework, energy can be flexibly used as a scoring function for any pre-trained neural classifier as well as a trainable cost function to shape the energy surface explicitly for OOD detection. On a CIFAR-10 pre-trained WideResNet, using the energy score reduces the average FPR (at TPR 95%) by 18.03% compared to the softmax confidence score. With energy-based training, our method outperforms the state-of-the-art on common benchmarks.

Subfields: Artificial Intelligence, Anomaly & Outlier Detection

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jun Zhu
  2. Mohit Bansal
  3. Ziwei Liu
  4. Fahad Shahbaz Khan
  5. Percy Liang
  6. Yoshua Bengio
  7. Quoc V. Le
  8. Bernt Schiele

In Anomaly & Outlier Detection

  1. Rui Huang
  2. Mohit Bansal
  3. Adyasha Maharana
  4. Yiyou Sun
  5. Zhen Fang
  6. K. J. Joseph
  7. Jie Lu
  8. Yue Zhao

Citations in the corpus