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.
arXiv commentAccepted to ICML 2021 Workshop on Uncertainty & Robustness in Deep Learning
References in corpus (21)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Wide Residual Networks
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Predictive Uncertainty Estimation via Prior Networks
- Deep Structured Energy Based Models for Anomaly Detection
- Glow: Generative Flow with Invertible 1x1 Convolutions
- WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
- Implicit Generation and Generalization in Energy-Based Models
- Sliced Score Matching: A Scalable Approach to Density and Score Estimation
- Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
- Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
- Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
- Prescribed Generative Adversarial Networks
- Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
- Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data
- Density of States Estimation for Out-of-Distribution Detection
- Building robust classifiers through generation of confident out of distribution examples
- No MCMC for me: Amortized sampling for fast and stable training of energy-based models
- Deep Residual Flow for Out of Distribution Detection