Affiliations: [a] School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, Jiangsu, China | [b] Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing, Jiangsu, China | [c] State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
Correspondence:
[*]
Corresponding author: Qing Tian, School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, Jiangsu 210044, China. E-mail: [email protected].
Abstract: Nowadays, the idea of active learning is gradually adopted to assist domain adaptation. However, due to the existence of domain shift, the traditional active learning methods originating from semi-supervised scenarios can not be directly applied to domain adaptation. To solve the problem, active domain adaptation is proposed as a new domain adaptation paradigm, which aims to improve the performance of the model by annotating a small amount of target domain samples. In this regard, we propose an active domain adaptation method named Boosting Active Domain Adaptation with Exploration of Samples (BADA), dividing Active DA into two related issues: sample selection and sample utilization. We design the instability selection criterion based on predictive consistency and the diversity selection criterion. For the remaining unlabeled samples, we design a self-training framework, which screens out reliable samples and unreliable samples through the sample screening mechanism similar to selection criteria. And we adopt respective loss functions for reliable samples and unreliable samples. Experiments show that BADA remarkably outperforms previous active learning methods and Active DA methods on several domain adaptation datasets.
Keywords: Domain adaptation, active learning, active domain adaptation, self-training
