Spectral Bisection Tree Guided Deep Adaptive Exemplar Autoencoder for Unsupervised Domain Adaptation

By Ming Shao, Zhengming Ding, Handong Zhao, Yun Raymond Fu. 2016

19 citations recorded by the source corpus.

Learning with limited labeled data is always a challenge in AI problems, and one of promising ways is transferring well-established source domain knowledge to the target domain, i.e., domain adaptation. In this paper, we extend the deep representation learning to domain adaptation scenario, and propose a novel deep model called ``Deep Adaptive Exemplar AutoEncoder (DAE$^2$)''. Different from conventional denoising autoencoders using corrupted inputs, we assign semantics to the input-output pairs of the autoencoders, which allow us to gradually extract discriminant features layer by layer. To this end, first, we build a spectral bisection tree to generate source-target data compositions as the training pairs fed to autoencoders. Second, a low-rank coding regularizer is imposed to ensure the transferability of the learned hidden layer. Finally, a supervised layer is added on top to transform learned representations into discriminant features. The problem above can be solved iteratively in an EM fashion of learning. Extensive experiments on domain adaptation tasks including object, handwritten digits, and text data classifications demonstrate the effectiveness of the proposed method.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Yun Raymond Fu
3. Tongliang Liu
4. Ming Shao
5. Mingming Gong
6. Hongfu Liu
7. Qiang Yang
8. Ya Li

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yun Raymond Fu
3. Qiang Yang
4. Tongliang Liu
5. Ming Shao
6. Mingming Gong
7. Xinmei Tian
8. Hongfu Liu

Citations in the corpus

• Domain Generalization via Conditional Invariant Representations (2018, background): “Domain adaptation is a related problem which has been extensively studied in the literature (Baktashmotlagh et al. 2013; Huang et al. 2007; Pan et al. 2011; Long et al. 2017; Shao, Kit, and Fu 2014; Shao et al. 2016; Luo et al. 2017; Liu, Yang, and Tao 2017; ?”
• Understanding How Feature Structure Transfers in Transfer Learning (2017, background): “The last decade has witnessed the success of various transfer learning algorithms [Shao et al., 2014; Long et al., 2015; Li et al., 2015; Liu et al., 2016; Shao et al., 2016] in exploiting the transfer of knowledge across domains.”
• Structure-Preserved Multi-source Domain Adaptation (2016, methodology): “Typical methods include finding intermediate subspaces that describe the smooth transition from one domain to another [8], [10], [14], [23], learning common features subspace [3], [24], [27], [29], [31] or deep features [6], [28].”