Topic: Performance-Enhancing Network Pruning for Crowd Counting
Speaker: Prof. Xiangjian He (University of Technology Sydney)
Time: 10:00 AM, July 15
Venue: B707, New Main Building
Crowd counting, for estimating the number of people in a crowd using vision based computer techniques, has attracted much interest in research community. Although many attempts have been reported, real world problems, such as huge variation in subjects’ sizes in images and serious occlusion among people, make it still a challenging problem. In this study, we propose an Adaptive Counting Convolutional Neural Network (A-CCNN) and consider the scale variation of objects in a frame adaptively so as to improve the accuracy of counting. The existing approaches also typically end up with a complicated network model resulting in a challenge for real-time processing. In our approach, a new pruning strategy is proposed by considering the contributions of various filters to the final classification. The filters in the original CCNN model are grouped into positive, negative and irrelevant types. We prune the irrelevant filters of which feature maps contain little information, and the negative filters determined by a mask learned on a training dataset. We demonstrate the advantages of our proposed approach on a crowd counting problem. Our experimental results on benchmark datasets show that the proposed network model improves the counting accuracy.
Biography of the Speaker:
Prof. Xiangjian He received his PhD degree in University of Technology, Sydney, Australia, in 1999. Since 1999, he has been with the Unniversity of Technology, Sydney, Australia. His research interests include image processing, network security, pattern recognition, computer vision and machine learning.
School of Instrumentation Science and Opto-electronics Engineering