Laplace Landmark Localization

被引:35
作者
Robinson, Joseph P. [1 ,2 ]
Li, Yuncheng [2 ]
Zhang, Ning [2 ]
Fu, Yun [1 ]
Tulyakov, Sergey [2 ]
机构
[1] Northeastern Univ, Boston, MA 02115 USA
[2] Snap Inc, Santa Monica, CA USA
来源
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) | 2019年
关键词
D O I
10.1109/ICCV.2019.01020
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Landmark localization in images and videos is a classic problem solved in various ways. Nowadays, with deep networks prevailing throughout machine learning, there are revamped interests in pushing facial landmark detectors to handle more challenging data. Most efforts use network objectives based on L-1 or L-2 norms, which have several disadvantages. First of all, the generated heatmaps translate to the locations of landmarks (i.e. confidence maps) from which predicted landmark locations (i.e. the means) get penalized without accounting for the spread: a high-scatter corresponds to low confidence and vice-versa. For this, we introduce a LaplaceKL objective that penalizes for low confidence. Another issue is a dependency on labeled data, which are expensive to obtain and susceptible to error. To address both issues, we propose an adversarial training framework that leverages unlabeled data to improve model performance. Our method claims state-of-the-art on all of the 300W benchmarks and ranks second-to-best on the Annotated Facial Landmarks in the Wild (AFLW) dataset. Furthermore, our model is robust with a reduced size: 1/8 the number of channels (i.e. 0.0398 MB) is comparable to the state-of-the-art in real-time on CPU. Thus, this work is of high practical value to real-life application.
引用
收藏
页码:10102 / 10111
页数:10
相关论文
共 48 条
[41]  
Zhang SY, 2018, IEEE IPCCC
[42]   Compact Representation of High-Dimensional Feature Vectors for Large-Scale Image Recognition and Retrieval [J].
Zhang, Yu ;
Wu, Jianxin ;
Cai, Jianfei .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (05) :2407-2419
[43]  
Zhang ZP, 2014, LECT NOTES COMPUT SC, V8694, P94, DOI 10.1007/978-3-319-10599-4_7
[44]   MLMDA: a machine learning approach to predict and validate MicroRNA-disease associations by integrating of heterogenous information sources [J].
Zheng, Kai ;
You, Zhu-Hong ;
Wang, Lei ;
Zhou, Yong ;
Li, Li-Ping ;
Li, Zheng-Wei .
JOURNAL OF TRANSLATIONAL MEDICINE, 2019, 17 (01)
[45]   Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [J].
Zhu, Jun-Yan ;
Park, Taesung ;
Isola, Phillip ;
Efros, Alexei A. .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :2242-2251
[46]  
Zhu SZ, 2015, PROC CVPR IEEE, P4998, DOI 10.1109/CVPR.2015.7299134
[47]  
Zhu XX, 2012, PROC CVPR IEEE, P2879, DOI 10.1109/CVPR.2012.6248014
[48]   Face Alignment Across Large Poses: A 3D Solution [J].
Zhu, Xiangyu ;
Lei, Zhen ;
Liu, Xiaoming ;
Shi, Hailin ;
Li, Stan Z. .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :146-155