Domain transfer convolutional attribute embedding

TL;DR

This paper introduces a transfer learning approach that uses convolutional neural networks to embed attributes into a common space, improving classification across different domains with stable attribute representations.

Contribution

It proposes a novel CNN-based attribute embedding method for transfer learning that combines domain-independent and domain-specific representations within a joint framework.

Findings

Effective attribute embedding improves cross-domain classification.

The method outperforms existing approaches on benchmark datasets.

Joint learning reduces classification and embedding errors.

Abstract

In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross different domains. This strongly motives us to learn effective domain transfer attribute representations. To this end, we proposed to embed the attributes of the data to a common space by using the powerful convolutional neural network (CNN) model. The convolutional representations of the data points are mapped to the corresponding attributes so that they can be effective embedding of the attributes. We also represent the data of different domains by a domain-independent CNN, ant a domain-specific CNN, and combine their outputs with the attribute embedding to build the classification model. An joint learning framework is constructed to minimize the classification errors, the attribute mapping error, the mismatching of the domain-independent representations cross different domains, and to encourage the the neighborhood smoothness of representations in the target domain. The minimization problem is solved by an iterative algorithm based on gradient descent. Experiments over benchmark data sets of person re-identification, bankruptcy prediction, and spam email detection, show the effectiveness of the proposed method.