NDLI: Domain Adaptation for Structured Regression

Content Provider	SpringerLink
Author	Yamada, Makoto Sigal, Leonid Chang, Yi
Copyright Year	2013
Abstract	Discriminative regression models have proved effective for many vision applications (here we focus on 3D full-body and head pose estimation from image and depth data). However, dataset bias is common and is able to significantly degrade the performance of a trained model on target test sets. As we show, covariate shift, a form of unsupervised domain adaptation (USDA), can be used to address certain biases in this setting, but is unable to deal with more severe structural biases in the data. We propose an effective and efficient semi-supervised domain adaptation (SSDA) approach for addressing such more severe biases in the data. Proposed SSDA is a generalization of USDA, that is able to effectively leverage labeled data in the target domain when available. Our method amounts to projecting input features into a higher dimensional space (by construction well suited for domain adaptation) and estimating weights for the training samples based on the ratio of test and train marginals in that space. The resulting augmented weighted samples can then be used to learn a model of choice, alleviating the problems of bias in the data; as an example, we introduce SSDA twin Gaussian process regression (SSDA-TGP) model. With this model we also address the issue of data sharing, where we are able to leverage samples from certain activities (e.g., walking, jogging) to improve predictive performance on very different activities (e.g., boxing). In addition, we analyze the relationship between domain similarity and effectiveness of proposed USDA versus SSDA methods. Moreover, we propose a computationally efficient alternative to TGP (Bo and Sminchisescu 2010), and it’s variants, called the direct TGP. We show that our model outperforms a number of baselines, on two public datasets: HumanEva and ETH Face Pose Range Image Dataset. We can also achieve 8–15 times speedup in computation time, over the traditional formulation of TGP, using the proposed direct formulation, with little to no loss in performance.
Starting Page	126
Ending Page	145
Page Count	20
File Format	PDF
ISSN	09205691
Journal	International Journal of Computer Vision
Volume Number	109
Issue Number	1-2
e-ISSN	15731405
Language	English
Publisher	Springer US
Publisher Date	2013-12-13
Publisher Place	Boston
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	3D pose estimation Semi-supervised domain adaptation Covariate shift adaptation Computer Imaging, Vision, Pattern Recognition and Graphics Artificial Intelligence (incl. Robotics) Image Processing and Computer Vision Pattern Recognition
Content Type	Text
Resource Type	Article
Subject	Artificial Intelligence Computer Vision and Pattern Recognition Software

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

Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation

Growing Regression Tree Forests by Classification for Continuous Object Pose Estimation

Metric Regression Forests for Correspondence Estimation

2D-3D Pose Estimation of Heterogeneous Objects Using a Region Based Approach

Real-Time Body Pose Recognition Using 2D or 3D Haarlets

Twin Gaussian Processes for Structured Prediction

Infinitesimal Plane-Based Pose Estimation

Pose Estimation of 3D Free-Form Contours

From 3D Point Clouds to Pose-Normalised Depth Maps

Domain Adaptation for Structured Regression

Similar Documents

Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation

Growing Regression Tree Forests by Classification for Continuous Object Pose Estimation

Metric Regression Forests for Correspondence Estimation

2D-3D Pose Estimation of Heterogeneous Objects Using a Region Based Approach

Real-Time Body Pose Recognition Using 2D or 3D Haarlets

Twin Gaussian Processes for Structured Prediction

Infinitesimal Plane-Based Pose Estimation

Pose Estimation of 3D Free-Form Contours

From 3D Point Clouds to Pose-Normalised Depth Maps

Domain Adaptation for Structured Regression