Unified Classification and Rejection: A One-versus-All Framework

Abstract

Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural network models usually excel in closed-set classification while performs poorly in rejecting OOD inputs. To tackle this problem, numerous methods have been designed to perform open set recognition (OSR) or OOD rejection/detection tasks. Previous methods mostly take post-training score transformation or hybrid models to ensure low scores on OOD inputs while separating known classes. In this paper, we attempt to build a unified framework for building open set classifiers for both classification and OOD rejection. We formulate the open set recognition of $K$-known-class as a $(K+1)$-class classification problem with model trained on known-class samples only. By decomposing the $K$-class problem into $K$ one-versus-all (OVA) binary classification tasks and binding some parameters, we show that combining the scores of OVA classifiers can give $(K+1)$-class posterior probabilities, which enables classification and OOD rejection in a unified framework. To maintain the closed-set classification accuracy of the OVA trained classifier, we propose a hybrid training strategy combining OVA loss and multi-class cross-entropy loss. We implement the OVA framework and hybrid training strategy on the recently proposed convolutional prototype network and prototype classifier on vision transformer (ViT) backbone. Experiments on popular OSR and OOD detection datasets demonstrate that the proposed framework, using a single multi-class classifier, yields competitive performance in closed-set classification, OOD detection, and misclassification detection.

Published in Machine Intelligence Research (https://link.springer.com/article/10.1007/s11633-024-1514-4)

References in corpus (24)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• End to End Learning for Self-Driving Cars
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Recent Advances in Open Set Recognition: A Survey
• 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
• Generalized Out-of-Distribution Detection: A Survey
• TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
• Learning Open Set Network with Discriminative Reciprocal Points
• Scaling Out-of-Distribution Detection for Real-World Settings
• OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
• VOS: Learning What You Don't Know by Virtual Outlier Synthesis
• Mitigating Neural Network Overconfidence with Logit Normalization
• ReAct: Out-of-distribution Detection With Rectified Activations
• On the Importance of Gradients for Detecting Distributional Shifts in the Wild
• Max-Mahalanobis Linear Discriminant Analysis Networks
• Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers
• Extremely Simple Activation Shaping for Out-of-Distribution Detection
• A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
• POEM: Out-of-Distribution Detection with Posterior Sampling
• Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
• Revisiting Discriminative vs. Generative Classifiers: Theory and Implications
• Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection
• Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data