文章方法:
1.Classification Model:Google net(smaller and faster) 相比较于VGG
2.使用Cascade Region Regression
(1)Increase the variation of initialization during training.
(2)Augment training data by removing 0.7 NMS step around GT after RPN.
(1)Increase the variation of initialization during training.
(2)Augment training data by removing 0.7 NMS step around GT after RPN.