Domain Adaptation for Structured Regression

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 s...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of computer vision Ročník 109; číslo 1-2; s. 126 - 145
Hlavní autoři: Yamada, Makoto, Sigal, Leonid, Chang, Yi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Boston Springer US 01.08.2014
Springer
Springer Nature B.V
Témata:
3-D graphics
Adaptation
Analysis
Artificial Intelligence
Bias
Computer Imaging
Computer Science
Datasets
Estimating
Image Processing and Computer Vision
Image processing systems
Information sharing
Linear algebra
Mathematical models
Pattern Recognition
Pattern Recognition and Graphics
Regression
Regression analysis
Studies
Three dimensional
Trains
Vision
Covariate shift adaptation
3D pose estimation
Semi-supervised domain adaptation
ISSN:0920-5691, 1573-1405
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-013-0689-x