Cross-domain attribute representation based on convolutional neural network

TL;DR

This paper introduces a novel domain transfer learning framework that leverages shared and domain-specific attribute representations using convolutional neural networks to improve classification across domains.

Contribution

It proposes a new CNN-based framework that models shared and domain-specific attributes for better transfer learning performance.

Findings

The model outperforms existing methods on benchmark datasets.

Shared attribute embedding enhances cross-domain classification.

Domain-specific features improve model adaptability.

Abstract

In the problem of domain transfer learning, we learn a model for the predic-tion in a target domain from the data of both some source domains and the target domain, where the target domain is in lack of labels while the source domain has sufficient labels. Besides the instances of the data, recently the attributes of data shared across domains are also explored and proven to be very helpful to leverage the information of different domains. In this paper, we propose a novel learning framework for domain-transfer learning based on both instances and attributes. We proposed to embed the attributes of dif-ferent domains by a shared convolutional neural network (CNN), learn a domain-independent CNN model to represent the information shared by dif-ferent domains by matching across domains, and a domain-specific CNN model to represent the information of each domain. The concatenation of the three CNN model outputs is used to predict the class label. An iterative algo-rithm based on gradient descent method is developed to learn the parameters of the model. The experiments over benchmark datasets show the advantage of the proposed model.