开集识别是一个新兴的研究领域,其目的是同时从预定义的类中分类样本,并将其余的识别为“未知”。在这个过程中,一个关键的挑战是减少从少量已知数据中学习到的众多未知样本的固有特征泛化的风险。本文提出了一个新的概念:互反点,它是每个已知范畴对应的类外空间的势表示。样本可以通过倒数点的差异性分为已知和未知两类。为了解决开集问题,我们提出了一个新的开放空间风险正则化项。基于倒易点构成的有界空间,通过多类别交互降低未知风险。互反点学习(Reciprocal Point Learning,RPL)是一种新的学习框架,它可以间接地将未知信息引入到只有已知类的学习器中,从而学习到更紧凑、更有区别的表示。此外,我们进一步构建了一个新的大规模具有挑战性的飞机数据集,用于开集识别:飞机300(Air-300)。在多个基准数据集上的大量实验表明,我们的框架明显优于其他现有的方法,并在标准开集基准上实现了最先进的性能。
英文摘要:
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.
Adversarial Reciprocal Points Learning for Open Set Recognition
Peking University(北京大学);Huawei(华为)
开集识别(Open Set Recognition,OSR)是机器学习的关键技术,其目标是同时对已知数据进行分类,并将未知数据识别为“未知”,其关键问题是如何同时降低已知数据的经验分类风险和未知数据的开空间风险。为了应对这一挑战,我们从多类整合的角度阐述了开放空间的风险问题,并使用一个新的概念互惠点来建模未开发的类外空间。在此基础上,提出了一种新的学习框架,称为对抗互点学习(ARPL),以最大限度地减少已知分布和未知分布的重叠,而不损失已知的分类精度。具体地说,每个倒易点都是通过类外空间与对应的已知类别学习的,并且多个已知类别之间的对抗被用来降低经验分类风险。然后,提出了一个对抗性的边缘约束,以减少开放空间的风险,通过限制潜在的开放空间所构成的倒易点。为了进一步估计开放空间中的未知分布,基于倒易点和已知类之间的对抗机制,设计了一种实例化的对抗增强方法来生成多样化和混乱的训练样本。这可以有效地提高模型对未知类的可扩展性。在各种基准数据集上的大量实验结果表明,该方法明显优于其他现有方法,并达到了最先进的性能。
Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
Institute for Infocomm Research, A*STAR(新加坡科技研究局资讯通信研究院);Nanyang Technological University(南洋理工大学);Centre for Frontier AI Research, A*STAR(新加坡科技研究局前沿人工智能研究中心);University of Cambridge(剑桥大学)
Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules
School of Software, Tsinghua University(清华大学软件学院);Department of Computer Science, University of Maryland at College Park(马里兰大学帕克分校计算机科学系);Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心)