「Computer Vision」Note on Deep Layer Cascade

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/dgyuanshaofeng/article/details/85561387

QQ Group: 428014259
Tencent E-mail：[email protected]
http://blog.csdn.net/dgyuanshaofeng/article/details/85561387

作者：Xiaoxiao Li, Ziwei Liu, Ping Luo, Chen Change Loy, Xiaoou Tang
单位：Department of Information Engineering, The Chinese University of Hong Kong; Shenzhen Key Lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology

Not All Pixels Are Equal，像素级难例挖掘或优化

0 摘要

1 介绍

2 相关工作

3 深层级联 Deep Layer Cascade

3.1 Turning a Deep Model into LC

3.2 Region Convolution

3.3 Training IRNet-LC

3.4 Relations with Previous Models

4 实验

5 结论

[1] Not All Pixels Are Equal Difficulty-aware Semantic Segmentation via Deep Layer Cascade CVPR 2017 [paper]