Safe-Student for Safe Deep Semi-Supervised Learning with Unseen-Class Unlabeled Data

Rundong He, Zhongyi Han, Xiankai Lu, Yilong Yin

Abstract

Deep semi-supervised learning (SSL) methods aim to take advantage of abundant unlabeled data to improve the algorithm performance. In this paper, we consider the problem of safe SSL scenario where unseen-class instances appear in the unlabeled data. This setting is essential and commonly appears in a variety of real applications. One intuitive solution is removing these unseen-class instances after detecting them during the SSL process. Nevertheless, the performance of unseen-class identification is limited by the small number of labeled data and ignoring the availability of unlabeled data. To take advantage of these unseen-class data and ensure performance, we propose a safe SSL method called SAFE-STUDENT from the teacher-student view. Firstly, a new scoring function called energy-discrepancy (ED) is proposed to help the teacher model improve the security of instances selection. Then, a novel unseen-class label distribution learning mechanism mitigates the unseen-class perturbation by calibrating the unseen-class label distribution. Finally, we propose an iterative optimization strategy to facilitate teacher-student network learning. Extensive studies on several representative datasets show that SAFE-STUDENT remarkably outperforms the state-of-the-art, verifying the feasibility and robustness of our method in the under-explored problem.
BibTeX
@inproceedings{he2022safe,
  author = {Rundong He and Zhongyi Han and Xiankai Lu and Yilong Yin},
  title = {{Safe-Student for Safe Deep Semi-Supervised Learning with Unseen-Class Unlabeled Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2022},
  doi = {10.1109/cvpr52688.2022.01418},
}

Loading related content...

Figure