NDLI: Random Subspace Supervised Descent Method for Regression Problems in Computer Vision

Content Provider	IEEE Xplore Digital Library
Author	Heng Yang Xuhui Jia Patras, I. Kwok-Ping Chan
Copyright Year	1994
Abstract	Supervised Descent Method (SDM) has shown good performance in solving non-linear least squares problems in computer vision, giving state of the art results for the problem of face alignment. However, when SDM learns the generic descent maps, it is very difficult to avoid over-fitting due to the high dimensionality of the input features. In this paper we propose a Random Subspace SDM (RSSDM) that maintains the high accuracy on the training data and improves the generalization accuracy. Instead of using all the features for descent learning at each iteration, we randomly select sub-sets of the features and learn an ensemble of descent maps in the corresponding subspaces, one in each subspace. Then, we average the ensemble of descents to calculate the update of the iteration. We test the proposed methods on two representative regression problems, namely, 3D pose estimation and face alignment and show that RSSDM consistently outperforms SDM in both tasks in terms of accuracy (e.g., RSSDM is able to localize 4% more landmarks at error level of 0.1 on the challenging iBug dataset). RSSDM also holds several useful generalization properties: 1) it is more effective when the number of training samples is small-with 3 Monte-Carlo permutations RSSDM can achieve similar performance to SDM with 9 Monte-Carlo permutations; 2) it is less sensitive to the changes of the strength of the regularization-when the regularization parameter is changed to 10 times larger, the mean error increases 9.0% for SDM vs. 3.4% for RSSDM.
Sponsorship	IEEE Signal Processing Society
Starting Page	1816
Ending Page	1820
Page Count	5
File Size	631269
File Format	PDF
ISSN	10709908
Volume Number	22
Issue Number	10
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-01-01
Publisher Place	U.S.A.
Access Restriction	One Nation One Subscription (ONOS)
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Face Three-dimensional displays Shape Training Estimation Feature extraction Computer vision supervised descent method 3D pose estimation face alignment random subspace
Content Type	Text
Resource Type	Article
Subject	Applied Mathematics Signal Processing Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Affine-Transformation Parameters Regression for Face Alignment

Pose-Invariant 3D Face Alignment

Global supervised descent method

Can 3D shape of the face reveal your age?

Fitting 3D Morphable Face Models using local features

Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Person-Specific Face Shape Estimation under Varying Head Pose from Single Snapshots

3-dimensional face pose and shape estimation based on relaxed model fitting optimization

Supervised Descent Method and Its Applications to Face Alignment

Random Subspace Supervised Descent Method for Regression Problems in Computer Vision

Similar Documents

Affine-Transformation Parameters Regression for Face Alignment

Pose-Invariant 3D Face Alignment

Global supervised descent method

Can 3D shape of the face reveal your age?

Fitting 3D Morphable Face Models using local features

Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Person-Specific Face Shape Estimation under Varying Head Pose from Single Snapshots

3-dimensional face pose and shape estimation based on relaxed model fitting optimization

Supervised Descent Method and Its Applications to Face Alignment

Random Subspace Supervised Descent Method for Regression Problems in Computer Vision