Boosting Active Learning via Improving Test Performance

Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test performance of the task model used in AL. In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in a better test performance. However, due to the lack of label information, directly computing gradient norm for unlabeled data is infeasible. To address this challenge, we propose two schemes, namely expected-gradnorm and entropy-gradnorm. The former computes the gradient norm by constructing an expected empirical loss while the latter constructs an unsupervised loss with entropy. Furthermore, we integrate the two schemes in a universal AL framework. We evaluate our method on classical image classification and semantic segmentation tasks. To demonstrate its competency in domain applications and its robustness to noise, we also validate our method on a cellular imaging analysis task, namely cryo-Electron Tomography subtomogram classification. Results demonstrate that our method achieves superior performance against the state of the art. We refer readers to https: //arxiv. org/pdf/2112. 05683. pdf for the full version of this paper which includes the appendix and source code link.

Authors

• Tianyang Wang Department of Computer Science, University of Alabama at Birmingham
• Xingjian Li Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, USA
• Pengkun Yang Center for Statistical Science, Tsinghua University
• Guosheng Hu Oosto
• Xiangrui Zeng
• Siyu Huang Harvard University
• Cheng-Zhong Xu University of Macau
• Min Xu

Keywords

No keywords are indexed for this paper.