20160907-30 禹之鼎:Large-Margin Softmax Loss for Convolutional Neural Networks ...

报告嘉宾：禹之鼎（Carnegie Mellon University）

报告时间：2016年09月07日（星期三）晚21:00（北京时间）

报告题目：Large-Margin Softmax Loss for Convolutional Neural Networks

主持人：朱鹏飞（天津大学）

报告摘要：

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not only can adjust the desired margin but also can avoid overfitting. We also show that the L-Softmax loss can be optimized by typical stochastic gradient descent. Extensive experiments on four benchmark datasets demonstrate that the deeply-learned features with L-softmax loss become more discriminative, hence significantly boosting the performance on a variety of visual classification and verification tasks. 

参考文献：

[1] Weiyang Liu, Yandong Wen, Zhiding Yu and Meng Yang. Large-Margin Softmax Loss for Convolutional Neural Networks. (ICML 2016)

报告人简介：

Zhiding Yu is a 5th year Ph.D. candidate with the Department of ECE, Carnegie Mellon University. He graduated from the Elite Class of EE, South China University of Technology in 2008 with B.Eng. degree, and obtained the M.Phil. degree from the Department of ECE, Hong Kong University of Science and Technology in 2012. His main research interests include structured prediction for scene understanding, object detection, clustering and image segmentation. He was twice the recipient of the HKTIIT Post-Graduate Excellence Scholarships (2010/2012). He is a co-author of the best student paper in International Symposium on Chinese Spoken Language Processing (ISCSLP) 2014, and the winner of best paper award in IEEE Winter Conference on Applications of Computer Vision (WACV) 2015. He did several interns at Adobe Research, Microsoft Research Redmond and Mitsubishi Electric Research Laboratories respectively in 2013, 2015 and 2016. His intern work on facial expression recognition at Microsoft Research won the First Runner Up at the EmotiW-SFEW Challenge 2015 and was integrated to the Microsoft Emotion Recognition API under Project Oxford.