Domain transfer convolutional attribute embedding

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 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 minimise the classification errors, the attribute mapping error, the mismatching of the domain-independent representations cross different domains, and to encourage the neighbourhood smoothness of representations in the target domain. The minimisation 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.本文针对属性数据下的迁移学习问题展开研究。在迁移学习任务中，我们希望借助辅助域与目标域的数据，为目标域的分类任务构建高效模型。而属性在不同域间天然具备稳定性，这一特性极大推动我们去学习有效的域迁移属性表征。为此，我们提出利用强大的卷积神经网络（Convolutional Neural Network, CNN）模型，将数据的属性嵌入至公共空间。将数据点的卷积表征映射至对应属性，以此实现属性的有效嵌入。此外，我们采用与域无关的卷积神经网络以及域专属卷积神经网络来表征不同域的数据，并将二者的输出与属性嵌入相结合，构建分类模型。我们构建了联合学习框架，以最小化分类误差、属性映射误差、域无关表征在不同域间的失配问题，并鼓励目标域内表征的邻域平滑性。该极小化问题通过基于梯度下降的迭代算法求解。在行人重识别、破产预测与垃圾邮件检测三类基准数据集上的实验结果，验证了所提方法的有效性。