Hao Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hao Xu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
C.-C. Jay Kuo
Ming Hsieh Department of Electrical Engineering, University of Southern California, 3740 McClintock Avenue, Los Angeles, CA, USA
1 shared publicationRuiyuan Lin
Ming Hsieh Department of Electrical Engineering, University of Southern California, 3740 McClintock Avenue, Los Angeles, CA, USA
1 shared publicationYueru Chen
Ming Hsieh Department of Electrical Engineering, University of Southern California, 3740 McClintock Avenue, Los Angeles, CA, USA
1 shared publication
Latest Publications
- Open Access
- 11 December 2018
- Published by Emerald Publishing in APSIPA Transactions on Signal and Information Processing
- Vol. 7 (1)
Understanding convolutional neural networks via discriminant feature analysis
Trained features of a convolution neural network (CNN) at different convolution layers is analyzed using two quantitative metrics 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 trained CNN features is validated by experimental results. Research on CNNs utilizing GCM and CPM tools offers important insights into its operational mechanism, including the behavior of trained CNN features and good detection performance of some object classes that were considered difficult in the past. Finally, the trained feature representation is compared between different CNN structures to explain the superiority of deeper networks.
- 11 December 2018
- Published by Emerald Publishing in APSIPA Transactions on Signal and Information Processing
- Vol. 7 (1)
Open AccessUnderstanding convolutional neural networks via discriminant feature analysis
Trained features of a convolution neural network (CNN) at different convolution layers is analyzed using two quantitative metrics 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 trained CNN features is validated by experimental results. Research on CNNs utilizing GCM and CPM tools offers important insights into its operational mechanism, including the behavior of trained CNN features and good detection performance of some object classes that were considered difficult in the past. Finally, the trained feature representation is compared between different CNN structures to explain the superiority of deeper networks.