Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices

Abstract

When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions. Detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to detect OOD examples by identifying inconsistencies between activity patterns and class predicted. We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates. We identify anomalies in the gram matrices by simply comparing each value with its respective range observed over the training data. Unlike many approaches, this can be used with any pre-trained softmax classifier and does not require access to OOD data for fine-tuning hyperparameters, nor does it require OOD access for inferring parameters. The method is applicable across a variety of architectures and vision datasets and, for the important and surprisingly hard task of detecting far-from-distribution out-of-distribution examples, it generally performs better than or equal to state-of-the-art OOD detection methods (including those that do assume access to OOD examples).

arXiv commentNeurIPS 2019 Workshop on Safety and Robustness in Decision Making

References in corpus (13)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• 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
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Deep Anomaly Detection with Outlier Exposure
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Predictive Uncertainty Estimation via Prior Networks
• Out-of-distribution Detection in Classifiers via Generation
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
• Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection
• Unsupervised Out-of-Distribution Detection with Batch Normalization
• A Variational Dirichlet Framework for Out-of-Distribution Detection
• Out-of-Distribution Detection Using Neural Rendering Generative Models

Cited by in corpus (7)

• Outlier Exposure with Confidence Control for Out-of-Distribution Detection
• SoK: Machine Learning Governance
• Temperature as Uncertainty in Contrastive Learning
• On the Out-of-distribution Generalization of Probabilistic Image Modelling
• Robust Representation Learning via Perceptual Similarity Metrics
• Improving Compositionality of Neural Networks by Decoding Representations to Inputs
• Out of distribution detection for skin and malaria images