基于球面正则化的支持向量描述视觉异常检测
Spherical regularized support vector description for visual anomaly detection
邓诗卓 1滕达 2李晓红 2陈佳祺 2陈东岳1
作者信息
- 1. 东北大学信息科学与工程学院 沈阳 110819;东北大学佛山研究生创新学院 佛山 528311
- 2. 东北大学信息科学与工程学院 沈阳 110819
- 折叠
摘要
异常检测作为视觉领域中一项独特而关键的任务,在医疗、安保等领域具有广泛的前景.异常检测目前受限于大规模异常数据标注,因此现有方法集中在单类分类和弱监督学习,深度支持向量描述(DeepSVDD)是实现单类分类的常见方法.然而,传统Deep SVDD在开展异常检测时往往面临球体崩塌.针对这一问题,提出了基于球面正则化的SVDD异常检测算法,通过引入软间隔损失与支持向量的思想,优化模型学习流程.进一步地,面向可标注样本,提出了基于SVDD的弱监督异常检测方法.在公开数据集MNIST和CIFAR-10上进行消融和对比实验,实验证明,相比于有监督算法,在MNIST数据集上,SR-WSVDD的性能提高了 3.7％,而在CIFAR-10数据集上则提高了 16.7％.此外,与其他弱监督算法相比,SR-WSVDD在CIFAR-10数据集上提升了 1.8％.所提出的SR-SVDD异常检测算法,弥补Deep SVDD容易发生球体崩塌的缺陷,使模型异常检测结果更加准确.
Abstract
Anomaly detection is an important task in the computer vision,such as medical,security.One of the challenges in anomaly detection is not easy to obtain large-scale annotated anomalous data.Existing methods focus on one-class classification and weakly supervised learning.Deep support vector data Description(Deep SVDD)is an important method to realize one-class anomaly detection.However,previous Deep SVDD often encounter the hypersphere collapse when constructing the model of the hypersphere.To solve this problem,support vector data description based on spherical regularization(SR-SVDD)is proposed in this paper.SR-SVDD applies the idea of support vectors to optimize the learning process by introducing slack terms.Furthermore,this paper proposes weakly supervised support vector data description based on spherical regularization(SR-WSVDD),which utilizes small amounts of labeled data.Ablation experiments and comparison experiments are carried out on MNIST and CIFAR-10.Experimental results show that,compared with supervised algorithms,the performance of SR-WSVDD is improved by 3.7％on the MNIST,and 16.7％on the CIFAR-10.In addition,compared with other weakly supervised algorithms,SR-WSVDD improves by 1.8％on CIFAR-10 dataset.The proposed SR-SVDD solves the spherical collapse of previous Deep SVDD,and makes the anomaly detection results more accurate.
关键词
计算机视觉/单类分类/弱监督学习/异常检测/自编码器/支持向量Key words
computer vision/one-class classification/weakly supervised learning/anomaly detection/autoencoder/support vector引用本文复制引用
基金项目
国家自然科学基金(62202087)
广东省基础与应用基础研究基金(2024A1515010244)
广东省基础与应用基础研究基金(2021B1515120064)
出版年
2024
NETL
NSTL
万方数据