Adversarial Reciprocal Points Learning for Open Set Recognition

Abstract

Open set recognition (OSR), aiming to simultaneously classify the seen classes and identify the unseen classes as 'unknown', is essential for reliable machine learning.The key challenge of OSR is how to reduce the empirical classification risk on the labeled known data and the open space risk on the potential unknown data simultaneously. To handle the challenge, we formulate the open space risk problem from the perspective of multi-class integration, and model the unexploited extra-class space with a novel concept Reciprocal Point. Follow this, a novel learning framework, termed Adversarial Reciprocal Point Learning (ARPL), is proposed to minimize the overlap of known distribution and unknown distributions without loss of known classification accuracy. Specifically, each reciprocal point is learned by the extra-class space with the corresponding known category, and the confrontation among multiple known categories are employed to reduce the empirical classification risk. Then, an adversarial margin constraint is proposed to reduce the open space risk by limiting the latent open space constructed by reciprocal points. To further estimate the unknown distribution from open space, an instantiated adversarial enhancement method is designed to generate diverse and confusing training samples, based on the adversarial mechanism between the reciprocal points and known classes. This can effectively enhance the model distinguishability to the unknown classes. Extensive experimental results on various benchmark datasets indicate that the proposed method is significantly superior to other existing approaches and achieves state-of-the-art performance.

arXiv commentIEEE-TPAMI,2021

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• Deep Anomaly Detection with Outlier Exposure
• The Extreme Value Machine
• Learning Open Set Network with Discriminative Reciprocal Points
• Good Semi-supervised Learning that Requires a Bad GAN
• Natural Adversarial Examples
• Reducing Network Agnostophobia
• Discriminative Probabilistic Prototype Learning
• Learning Bounds for Open-Set Learning

Cited by in corpus (17)

• Collective Decision of One-vs-Rest Networks for Open Set Recognition
• Embrace Limited and Imperfect Training Datasets: Opportunities and Challenges in Plant Disease Recognition Using Deep Learning
• Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
• Open-World Object Detection via Discriminative Class Prototype Learning
• Learning Discriminative Representations and Decision Boundaries for Open Intent Detection
• ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery
• Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology
• Understanding Open-Set Recognition by Jacobian Norm and Inter-Class Separation
• Adversarial Motorial Prototype Framework for Open Set Recognition
• Hybrid Open-set Segmentation with Synthetic Negative Data
• Open-Set Biometrics: Beyond Good Closed-Set Models
• Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalization
• Understanding the limitations of self-supervised learning for tabular anomaly detection
• On the link between generative semi-supervised learning and generative open-set recognition
• BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
• Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
• Familiarity-Based Open-Set Recognition Under Adversarial Attacks