Learning Open Set Network with Discriminative Reciprocal Points

Abstract

Open set recognition is an emerging research area that aims to simultaneously classify samples from predefined classes and identify the rest as 'unknown'. In this process, one of the key challenges is to reduce the risk of generalizing the inherent characteristics of numerous unknown samples learned from a small amount of known data. In this paper, we propose a new concept, Reciprocal Point, which is the potential representation of the extra-class space corresponding to each known category. The sample can be classified to known or unknown by the otherness with reciprocal points. To tackle the open set problem, we offer a novel open space risk regularization term. Based on the bounded space constructed by reciprocal points, the risk of unknown is reduced through multi-category interaction. The novel learning framework called Reciprocal Point Learning (RPL), which can indirectly introduce the unknown information into the learner with only known classes, so as to learn more compact and discriminative representations. Moreover, we further construct a new large-scale challenging aircraft dataset for open set recognition: Aircraft 300 (Air-300). Extensive experiments on multiple benchmark datasets indicate that our framework is significantly superior to other existing approaches and achieves state-of-the-art performance on standard open set benchmarks.

ECCV 2020 (spotlight)

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
• 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
• Reducing Network Agnostophobia
• Do Deep Generative Models Know What They Don't Know?

Cited by in corpus (12)

• Adversarial Reciprocal Points Learning for Open Set Recognition
• Generalized Out-of-Distribution Detection: A Survey
• Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
• Open-World Object Detection via Discriminative Class Prototype Learning
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Unified Classification and Rejection: A One-versus-All Framework
• M2IOSR: Maximal Mutual Information Open Set Recognition
• Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection
• Deep Metric Learning for Open World Semantic Segmentation
• BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
• Annotation-Efficient Untrimmed Video Action Recognition
• Taking Class Imbalance Into Account in Open Set Recognition Evaluation