报告题目：Discrimination-aware Channel Pruning for Deep Neural Networks
报 告 人：谭明奎 教授（华南理工大学）
报告时间：2019年4月12日（周五）上午9 ：00
报告地点：安徽大学磬苑校区理工D楼318会议室
报告摘要：Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature maps and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, whilst the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we investigate a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose those channels that really contribute to discriminative power. To this end, we introduce additional discrimination-aware losses into the network to increase the discriminative power of intermediate layers and then select the most discriminative channels for each layer by considering the additional loss and the reconstruction error. Last, we propose a greedy algorithm to conduct channel selection and parameter optimization in an iterative way. Extensive experiments demonstrate the effectiveness of our method. For example, on ILSVRC-12, our pruned ResNet-50 with 30% reduction of channels outperforms the baseline model by 0.39% in top-1 accuracy.
欢迎各位老师、同学届时前往！
科学技术处
2019年4月10日