Group visualization of class-discriminative features
Group visualization of class-discriminative features
复制标题
DOI：
10.1016/j.neunet.2020.05.026
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Rui Shi;Tianxing Li;Yasushi Yamaguchi
中科院分区：
文献类型：
--
作者：
Rui Shi;Tianxing Li;Yasushi Yamaguchi
解释卷积神经网络（CNN）行为的研究在过去几年中引起了很多关注。尽管已经提出了许多可视化方法来解释网络预测，但大多数都未能提供目标输出与卷积层提取的特征之间的明确相关性。在这项工作中，我们定义了一个概念，即，类别区分特征组，以指定由与特定图像类别相关的卷积核组提取的特征。我们提出了一种检测方法来检测类判别特征组和一种可视化方法来突出与特定输出相关的图像区域，并直观地解释类判别特征组。实验结果表明，该方法可以根据图像类别进行特征分类，并能明确从图像的哪些区域提取哪些特征组。我们还应用这种方法来可视化对抗样本中的“丢失”特征和包含非类对象的图像中的特征，以展示其调试网络失败或成功的能力。
Research explaining the behavior of convolutional neural networks (CNNs) has gained a lot of attention over the past few years. Although many visualization methods have been proposed to explain network predictions, most fail to provide clear correlations between the target output and the features extracted by convolutional layers. In this work, we define a concept, i.e., class-discriminative feature groups, to specify features that are extracted by groups of convolutional kernels correlated with a particular image class. We propose a detection method to detect class-discriminative feature groups and a visualization method to highlight image regions correlated with particular output and to interpret class-discriminative feature groups intuitively. The experiments showed that the proposed method can disentangle features based on image classes and shed light on what feature groups are extracted from which regions of the image. We also applied this method to visualize “lost” features in adversarial samples and features in an image containing a non-class object to demonstrate its ability to debug why the network failed or succeeded.