Continuous Supervised Descent Method for Facial Landmark Localisation

2017 ◽  
pp. 121-135 ◽  
Author(s):  
Marc Oliu ◽  
Ciprian Corneanu ◽  
László A. Jeni ◽  
Jeffrey F. Cohn ◽  
Takeo Kanade ◽  
...  
Keyword(s):  
Descent Method ◽  
Facial Landmark ◽  
Supervised Descent Method

Multi-template supervised descent method for face alignment

2021 ◽  
Vol 65 ◽  
pp. 107-117
Author(s):  
Cheng Ding ◽  
Weidong Tian ◽  
Chao Geng ◽  
Xijing Zhu ◽  
Qinmu Peng ◽  
...  
Keyword(s):  
Descent Method ◽  
Face Alignment ◽  
Supervised Descent Method

Neural network-based supervised descent method for 2D electrical impedance tomography

2020 ◽  
Vol 41 (7) ◽  
pp. 074003
Author(s):  
Zhichao Lin ◽  
Rui Guo ◽  
Ke Zhang ◽  
Maokun Li ◽  
Fan Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Electrical Impedance Tomography ◽  
Electrical Impedance ◽  
Descent Method ◽  
Impedance Tomography ◽  
Supervised Descent Method

Application of supervised descent method for transient EM data inversion

2018 ◽  
Author(s):  
Rui Guo ◽  
Maokun Li ◽  
Fan Yang ◽  
Shengheng Xu ◽  
Guangyou Fang ◽  
...  
Keyword(s):  
Descent Method ◽  
Data Inversion ◽  
Supervised Descent Method

Application of supervised descent method to transient electromagnetic data inversion

Geophysics ◽  
2019 ◽  
Vol 84 (4) ◽  
pp. E225-E237 ◽  
Author(s):  
Rui Guo ◽  
Maokun Li ◽  
Guangyou Fang ◽  
Fan Yang ◽  
Shenheng Xu ◽  
...  
Keyword(s):  
Prior Information ◽  
Descent Method ◽  
Training Data ◽  
Data Set ◽  
Data Inversion ◽  
Transient Electromagnetic ◽  
Online Computation ◽  
Training Stage ◽  
Highly Nonlinear ◽  
Supervised Descent Method

Inversion plays an important role in transient electromagnetic (TEM) data interpretation. This problem is highly nonlinear and severely ill posed. Gradient-descent methods have been widely used to invert TEM data, and regularization schemes containing prior information are applied to reduce the nonuniqueness and stabilize the inversion. During the inversion, the partial derivatives are repeatedly computed, which is time and memory consuming. Furthermore, regularization schemes can only provide limited prior information. Much prior information from knowledge and experience cannot be directly used in inversion. In this work, we applied the supervised descent method (SDM) to TEM data inversion. This method contains an offline training stage and an online prediction stage. In the training stage, a training data set is generated according to prior information. Then, the average descent direction between a fixed initial model and the training models can be learned by iterative schemes. In the online stage of prediction, the learned descent directions are applied directly into the inversion to update the models. In this manner, one can select models satisfying the data and model misfit. In this study, SDM is applied to model- and pixel-based inversion schemes. Synthetic examples indicate that SDM inversion can not only enhance the accuracy of inversion due to the incorporation of prior information but also largely accelerate the inversion procedure because it avoids the online computation of derivatives.

Random Subspace Supervised Descent Method for Regression Problems in Computer Vision

2015 ◽  
Vol 22 (10) ◽  
pp. 1816-1820 ◽  
Author(s):  
Heng Yang ◽  
Xuhui Jia ◽  
Ioannis Patras ◽  
Kwok-Ping Chan
Keyword(s):  
Computer Vision ◽  
Descent Method ◽  
Random Subspace ◽  
Supervised Descent Method ◽  
Regression Problems
Sign in / Sign up

Export Citation Format

Share Document