Geometric robustness of deep networks: analysis and improvement

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(2017)

引用 151|浏览145
暂无评分
摘要
Deep convolutional neural networks have been shown to be vulnerable to arbitrary geometric transformations. However, there is no systematic method to measure the invariance properties of deep networks to such transformations. We propose ManiFool as a simple yet scalable algorithm to measure the invariance of deep networks. In particular, our algorithm measures the robustness of deep networks to geometric transformations in a worst-case regime as they can be problematic for sensitive applications. Our extensive experimental results show that ManiFool can be used to measure the invariance of fairly complex networks on high dimensional datasets and these values can be used for analyzing the reasons for it. Furthermore, we build on Manifool to propose a new adversarial training scheme and we show its effectiveness on improving the invariance properties of deep neural networks.
更多
查看译文
关键词
geometric robustness,deep networks,convolutional neural networks,arbitrary geometric transformations,invariance properties,ManiFool,deep neural networks
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