On Out-of-distribution Detection with Energy-based Models
arXiv:2107.08785
Abstract
Several density estimation methods have shown to fail to detect out-of-distribution (OOD) samples by assigning higher likelihoods to anomalous data. Energy-based models (EBMs) are flexible, unnormalized density models which seem to be able to improve upon this failure mode. In this work, we provide an extensive study investigating OOD detection with EBMs trained with different approaches on tabular and image data and find that EBMs do not provide consistent advantages. We hypothesize that EBMs do not learn semantic features despite their discriminative structure similar to Normalizing Flows. To verify this hypotheses, we show that supervision and architectural restrictions improve the OOD detection of EBMs independent of the training approach.
Accepted to ICML 2021 Workshop on Uncertainty & Robustness in Deep Learning
References in corpus (5)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Sliced Score Matching: A Scalable Approach to Density and Score Estimation
- Prescribed Generative Adversarial Networks
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data
- Density of States Estimation for Out-of-Distribution Detection