arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.03438cs.CV
收藏

基于卷积原型学习的鲁棒分类

Robust Classification with Convolutional Prototype Learning

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);CAS Center for Excellence of Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心)

Hong-Ming Yang, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu

摘要:

卷积神经网络(CNN)已广泛用于图像分类。尽管准确率很高,但CNN已经被证明很容易被一些对抗性的例子所欺骗,这表明CNN对于模式分类来说不够鲁棒。在本文中,我们认为CNN缺乏鲁棒性是由softmax层造成的,softmax层是一个完全区分的模型,并且基于封闭世界的假设(即,有固定数量的类别)。为了提高鲁棒性,我们提出了一种新的学习框架,称为卷积原型学习(CPL)。使用原型的优点是它可以很好地处理开放世界识别问题,从而提高鲁棒性。在CPL的框架下,设计了多种分类准则对网络进行训练。此外,原型损失(PL)被提出作为一个正则化,以提高类内紧凑性的特征表示,它可以被看作是一个生成模型的基础上高斯假设的不同类别。在多个数据集上的实验表明,CPL可以获得与传统CNN相当甚至更好的结果,并且从鲁棒性的角度来看,CPL在拒绝和增量类别学习任务中都表现出很大的优势。

英文摘要:

Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern classification. In this paper, we argue that the lack of robustness for CNN is caused by the softmax layer, which is a totally discriminative model and based on the assumption of closed world (i.e., with a fixed number of categories). To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL). The advantage of using prototypes is that it can well handle the open world recognition problem and therefore improve the robustness. Under the framework of CPL, we design multiple classification criteria to train the network. Moreover, a prototype loss (PL) is proposed as a regularization to improve the intra-class compactness of the feature representation, which can be viewed as a generative model based on the Gaussian assumption of different classes. Experiments on several datasets demonstrate that CPL can achieve comparable or even better results than traditional CNN, and from the robustness perspective, CPL shows great advantages for both the rejection and incremental category learning tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑