Abstract | ||
---|---|---|
In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data. Rather than using a max-pooling layer followed one convolutional layer in typical convolutional neural networks (CNN), SDN adopts a stack of 3 layer groups instead. Each group layer contains two convolutional layers and a max-pooling layer, which can extract the features hierarchically. Moreover, an effective data augmentation strategy and corresponding training skills are also proposed to over-come the lack of training images on COFW and 300-W da-tasets. The experiment results show that our method outper-forms state-of-the-art methods in both detection accuracy and speed. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Computer Vision and Pattern Recognition | Training set,Pattern recognition,Computer science,Convolutional neural network,Training skills,Speech recognition,Artificial intelligence,Landmark,Machine learning |
DocType | Volume | Citations |
Journal | abs/1702.02719 | 0 |
PageRank | References | Authors |
0.34 | 10 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zongping Deng | 1 | 0 | 0.34 |
Ke Li | 2 | 19 | 10.38 |
Qijun Zhao | 3 | 419 | 38.37 |
Zhang Yi | 4 | 356 | 37.14 |
Hu Chen | 5 | 150 | 17.55 |