Knowledge Commons of Institute of Automation,CAS
Robust Classification with Convolutional Prototype Learning | |
Hong-Ming Yang1,2; Xu-Yao Zhang1,2; Fei Yin1,2; Cheng-Lin Liu1,2 | |
2018 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
会议日期 | 2018-06-18 |
会议地点 | Salt Lake City, Utah, USA |
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. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44417 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
作者单位 | 1.NLPR, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Hong-Ming Yang,Xu-Yao Zhang,Fei Yin,et al. Robust Classification with Convolutional Prototype Learning[C],2018. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论