应计算机学院感知计算中心左旺孟教授邀请，天津大学王旗龙博士将于12月20日对计算机学院感知计算中心进行访问，访问期间将举行学术报告并进行交流，欢迎各位感兴趣的师生参加。

题目：What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective

时间：12月20日 10:00

地点：综合楼701

嘉宾：王旗龙博士

摘要：Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task. Despite considerable advance, the reasons on effectiveness of GCP on deep CNNs have not been well studied. In this paper, we make an attempt to understand what deep CNNs benefit from GCP in a viewpoint of optimization. Specifically, we show that GCP can make the optimization landscape more smooth and the gradients more predictive. Furthermore, we discuss the connection between GCP and second-order optimization for deep CNNs. More importantly, above findings can account for several merits of covariance pooling for training deep CNNs that have not been recognized previously or fully explored, including significant acceleration of network convergence, stronger robustness to distorted examples generated by image corruptions and perturbations, and good generalization ability to different vision tasks. We conduct extensive experiments using various deep CNN architectures on diversified tasks, and the results provide strong support to our findings.

嘉宾简介：天津大学智能与计算学部助理教授，2018年毕业于大连理工大学，获得博士学位，主要研究方向为深度学习，概率分布建模和视频图像分析。目前在国际顶级会议CVPR/ICCV/ECCV/NIPS/IJCAI以及IEEE T-PAMI/IEEE T-IP/IEEE T-CSVT等其他国际权威会议期刊共发表学术论文30余篇。曾获2015年阿里巴巴大规模图像检索大赛第二名(2/853)、ICIP2015 Best 10% paper。CVPR, ICCV, ECCV, IJCAI, AAAI等会议以及IEEE T-IP, T-NNLS等期刊审稿人。入选2018年博士后创新人才计划，获得国家自然科学基金青年基金以及博士后基金等资助