Domain Adaptation for Structured Regression
Domain Adaptation for Structured Regression
复制标题
DOI：
10.1007/s11263-013-0689-x
复制
发表时间：
2013-12
影响因子：
19.5
通讯作者：
M. Yamada;L. Sigal;Yi Chang
中科院分区：
文献类型：
--
作者：
M. Yamada;L. Sigal;Yi Chang
判别回归模型已被证明对许多视觉应用是有效的（在这里，我们专注于从图像和深度数据中估计3D全身和头部姿势）。然而，数据集偏见是常见的，并且能够显着降低目标测试集上训练模型的性能。正如我们所展示的，协变量移位，一种无监督域自适应（USDA）的形式，可以用来解决这种情况下的某些偏差，但无法处理数据中更严重的结构性偏差。我们提出了一种有效和高效的半监督域自适应（SSDA）方法来解决数据中的这种更严重的偏差。建议的SSDA是USDA的推广，能够有效地利用目标域中可用的标记数据。我们的方法相当于将输入特征投影到更高维的空间中（通过适合域自适应的构造），并根据该空间中测试和训练边缘的比率估计训练样本的权重。由此产生的增强加权样本然后可以用于学习选择的模型，减轻数据中的偏差问题;作为一个例子，我们介绍了SSDA双高斯过程回归（SSDA-TGP）模型。有了这个模型，我们还解决了数据共享的问题，我们能够利用某些活动的样本（例如，步行，慢跑）以改善对非常不同的活动（例如，拳击）。此外，我们分析了域相似性和建议USDA与SSDA方法的有效性之间的关系。此外，我们提出了一个计算效率高的替代TGP（Bo和Sminchisescu 2010），它的变种，称为直接TGP。我们证明了我们的模型在两个公共数据集上的表现优于一些基线：HumanEva和ETH Face Pose Range Image Dataset。我们还可以实现8-15倍的加速计算时间，在传统的制定TGP，使用建议的直接制定，几乎没有损失的性能。
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 biasis 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 ofdata 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.