Robust Classification with Convolutional Prototype Learning

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(2018)

引用 299|浏览104
暂无评分
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.
更多
查看译文
关键词
multiple classification criteria,intra-class compactness,Gaussian assumption,CNN,robustness perspective,prototype loss,open world recognition problem,CPL,novel learning framework,totally discriminative model,softmax layer,pattern classification,adversarial examples,image classification,convolutional neural networks,convolutional prototype learning,robust classification,incremental category learning tasks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要