Understanding CNN via deep features analysis
Hao Xu, Yueru Chen, Ruiyuan Lin, C.‐C. Jay Kuo · 2017
Two quantitative metrics are proposed for evaluating trained deep features at different convolution layers in this work. We first show mathematically that the Gaussian confusion measure (GCM) can be used to identify the discriminative ability of an individual feature. Next, we generalize this idea, introduce another measure called the cluster purity measure (CPM), and use it to analyze the discriminative ability of multiple features jointly. The discriminative ability of the trained Convolution Neural Network (CNN) features is confirmed by experiments. Further studies utilizing GCM and CPM as tools offer important insights into the CNN, such as understanding the behavior of trained CNN features and the good detection performance of some object classes that were considered difficult in the past. Finally, the trained deep feature representation is compared between different CNN structures to validate the superiority of deeper networks.