Deep multi-center learning for face alignment
| Autor: | Lizhuang Ma, Yangyang Hao, Xin Tan, Zhiwen Shao, Hengliang Zhu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Cognitive Neuroscience Deep learning Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition 02 engineering and technology Computer Science Applications 020901 industrial engineering & automation Artificial Intelligence Face (geometry) 0202 electrical engineering electronic engineering information engineering Code (cryptography) 020201 artificial intelligence & image processing Center (algebra and category theory) Artificial intelligence Layer (object-oriented design) business |
| Zdroj: | Neurocomputing. 396:477-486 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2018.11.108 |
| Popis: | Facial landmarks are highly correlated with each other since a certain landmark can be estimated by its neighboring landmarks. Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks. In this paper, we propose a novel deep learning framework named Multi-Center Learning with multiple shape prediction layers for face alignment. In particular, each shape prediction layer emphasizes on the detection of a certain cluster of semantically relevant landmarks respectively. Challenging landmarks are focused firstly, and each cluster of landmarks is further optimized respectively. Moreover, to reduce the model complexity, we propose a model assembling method to integrate multiple shape prediction layers into one shape prediction layer. Extensive experiments demonstrate that our method is effective for handling complex occlusions and appearance variations with real-time performance. The code for our method is available at https://github.com/ZhiwenShao/MCNet-Extension. This paper has been accepted by Neurocomputing |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect