Improving the Generalization Ability of Deep Neural Networks for Cross-Domain Visual Recognition

Feature learning with deep neural networks (DNNs) has made remarkable progress in recent years. However, its data-driven nature makes the collection of labeled training data expensive or impossible when the testing domain changes. Here, we propose a method of transferable feature learning and instance-level adaptation to improve the generalization ability of DNNs so as to mitigate the domain shift challenge for cross-domain visual recognition. When less labeled information is available, our proposed method shows attractive results in the new target domain and outperforms the typical fine-tuning method. Two DNNs are chosen as the representatives working with our proposed method, to do a comprehensive study about the generalization ability on the tasks of image-to-image transfer, image-to-video transfer, multidomain image classification, and weakly supervised detection. The experimental results show that our proposed method is superior to other existing works in the literature. In addition, a large scale of cross-domain database is merged from three different domains, providing a quantitative platform to evaluate different approaches in the field of cross-domain object detection.

Automated summary

This study proposes a transferable feature learning and instance-level adaptation method to enhance the generalization ability of deep neural networks and alleviate domain shift challenge in cross-domain visual recognition. Experimental results demonstrate the method's superior performance in the new target domain and across multiple tasks compared to existing methods.