Outlier Exposure with Confidence Control for Out-of-Distribution Detection

Abstract

Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from novel class distributions and therefore, most of the existent classification algorithms assume that all classes are known prior to the training stage. In this work, we propose a methodology for training a neural network that allows it to efficiently detect out-of-distribution (OOD) examples without compromising much of its classification accuracy on the test examples from known classes. We propose a novel loss function that gives rise to a novel method, Outlier Exposure with Confidence Control (OECC), which achieves superior results in OOD detection with OE both on image and text classification tasks without requiring access to OOD samples. Additionally, we experimentally show that the combination of OECC with state-of-the-art post-training OOD detection methods, like the Mahalanobis Detector (MD) and the Gramian Matrices (GM) methods, further improves their performance in the OOD detection task, demonstrating the potential of combining training and post-training methods for OOD detection.

arXiv commentAccepted as a Journal paper at Neurocomputing. PyTorch code available at https://github.com/nazim1021/OOD-detection-using-OECC

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• Distilling the Knowledge in a Neural Network
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• A Simple Framework for Contrastive Learning of Visual Representations
• On Calibration of Modern Neural 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
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• Deep Anomaly Detection with Outlier Exposure
• Regularizing Neural Networks by Penalizing Confident Output Distributions
• Predictive Uncertainty Estimation via Prior Networks
• Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
• Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
• Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions
• WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
• Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
• Contrastive Training for Improved Out-of-Distribution Detection
• Open Category Detection with PAC Guarantees
• Discriminative out-of-distribution detection for semantic segmentation
• Novelty Detection with GAN
• Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
• Density of States Estimation for Out-of-Distribution Detection

Cited by in corpus (14)

• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
• Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples
• ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
• MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
• One Versus all for deep Neural Network Incertitude (OVNNI) quantification
• What is Wrong with One-Class Anomaly Detection?
• $k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
• Provably Robust Detection of Out-of-distribution Data (almost) for free
• Conditioning Latent-Space Clusters for Real-World Anomaly Classification
• Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection
• Out-distribution aware Self-training in an Open World Setting
• Why Should we Combine Training and Post-Training Methods for Out-of-Distribution Detection?
• Probabilistic Trust Intervals for Out of Distribution Detection
• Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding