MMM
YYYY
Adversarial Reciprocal Points Learning for Open Set Recognition
开放集识别的对抗性互反点学习
オープンセット認識のための敵対的逆点学習
개방 집합 식별 에서 의 대항 성 상호 반 점 학습
Aprendizaje de puntos de reacción mutua en el reconocimiento de conjuntos abiertos
L'apprentissage des points d'opposition mutuelle dans la reconnaissance des ensembles ouverts
изучение противоположных точек в распознавании открытых наборов
Guangyao Chen 陈光耀 ¹, Peixi Peng 彭佩玺 ¹, Xiangqian Wang ², Yonghong Tian 田永鸿 ¹
¹ School of Electronics Engineering and Computer Science, Peking University, 12465 Beijing, Beijing, China, 100871
中国 北京 北京大学信息科学技术学院
² AI Application Research Center, Huawei Technologies Co Ltd, 115371 Shenzhen, Guangdong, China
中国 广东 深圳 华为技术有限公司 AI应用研究中心
IEEE Transactions on Pattern Analysis and Machine Intelligence, 24 August 2021
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 Adversarial Reciprocal Point Learning framework 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.

An adversarial margin constraint is proposed to reduce the open space risk by limiting the latent open space constructed by reciprocal points. Moreover, an instantiated adversarial enhancement method is designed to generate diverse and confusing training samples. Extensive experimental results on various benchmark datasets indicate that the proposed method is significantly superior to existing approaches and achieves state-of-the-art performance.
IEEE Transactions on Pattern Analysis and Machine Intelligence_1
IEEE Transactions on Pattern Analysis and Machine Intelligence_2
IEEE Transactions on Pattern Analysis and Machine Intelligence_3
Reviews and Discussions
https://www.hotpaper.io/index.html
Self-polarized RGB device realized by semipolar micro-LEDs and perovskite-in-polymer films for backlight applications
A highly sensitive LITES sensor based on a multi-pass cell with dense spot pattern and a novel quartz tuning fork with low frequency
Multi-wavelength nanowire micro-LEDs for future high speed optical communication
Luminescence regulation of Sb3+ in 0D hybrid metal halides by hydrogen bond network for optical anti-counterfeiting
Breaking the optical efficiency limit of virtual reality with a nonreciprocal polarization rotator
Simultaneously realizing thermal and electromagnetic cloaking by multi-physical null medium
Generation of lossy mode resonances (LMR) using perovskite nanofilms
Acousto-optic scanning multi-photon lithography with high printing rate
Tailoring electron vortex beams with customizable intensity patterns by electron diffraction holography
Miniature tunable Airy beam optical meta-device
Data-driven polarimetric imaging: a review
Robust measurement of orbital angular momentum of a partially coherent vortex beam under amplitude and phase perturbations



Previous Article                                Next Article
About
|
Contact
|
Copyright © Hot Paper