数学学科Seminar第2520讲 基于点的网络通道修剪

创建时间:  2023/11/01  龚惠英   浏览次数:   返回

报告题目 (Title):CP3: Channel Pruning Plug-in for Point-based Networks(基于点的网络通道修剪)

报告人 (Speaker): 沈超敏 副教授(华东师范大学)

报告时间 (Time):2023年11月2日(周四) 8:30

报告地点 (Place):校本部 F420

邀请人(Inviter):温智婕

主办部门:永利数学系

报告摘要: In this talk, we propose a model called CP3, which is a Channel Pruning Plug-in for Point-based network. CP3 is elaborately designed to leverage the characteristics of point clouds and PNNs in order to enable 2D channel pruning methods for PNNs. Specifically, it presents a coordinate-enhanced channel importance metric to reflect the correlation between dimensional information and individual channel features, and it recycles the discarded points in PNN’s sampling process and reconsiders their potentially-exclusive information to enhance the robustness of channel pruning. Experiments on various PNN architectures show that CP3 constantly improves state-of-the-art 2D CNN pruning approaches on different point cloud tasks.

上一条:数学学科Seminar第2521讲 Hirota双线性方法在构造可积系统有理解与半有理解中的应用

下一条:数学学科Seminar第2519讲 基于深度学习的医学图像质量增强和分割


数学学科Seminar第2520讲 基于点的网络通道修剪

创建时间:  2023/11/01  龚惠英   浏览次数:   返回

报告题目 (Title):CP3: Channel Pruning Plug-in for Point-based Networks(基于点的网络通道修剪)

报告人 (Speaker): 沈超敏 副教授(华东师范大学)

报告时间 (Time):2023年11月2日(周四) 8:30

报告地点 (Place):校本部 F420

邀请人(Inviter):温智婕

主办部门:永利数学系

报告摘要: In this talk, we propose a model called CP3, which is a Channel Pruning Plug-in for Point-based network. CP3 is elaborately designed to leverage the characteristics of point clouds and PNNs in order to enable 2D channel pruning methods for PNNs. Specifically, it presents a coordinate-enhanced channel importance metric to reflect the correlation between dimensional information and individual channel features, and it recycles the discarded points in PNN’s sampling process and reconsiders their potentially-exclusive information to enhance the robustness of channel pruning. Experiments on various PNN architectures show that CP3 constantly improves state-of-the-art 2D CNN pruning approaches on different point cloud tasks.

上一条:数学学科Seminar第2521讲 Hirota双线性方法在构造可积系统有理解与半有理解中的应用

下一条:数学学科Seminar第2519讲 基于深度学习的医学图像质量增强和分割

Baidu
sogou