English

R2-D2: Repetitive Reprediction Deep Decipher for Semi-Supervised Deep Learning

Computer Vision and Pattern Recognition 2022-02-21 v1 Artificial Intelligence

Abstract

Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parameters iteratively. However, they lack theoretical support and cannot explain why predictions are good candidates for pseudo-labels in the deep learning paradigm. In this paper, we propose a principled end-to-end framework named deep decipher (D2) for SSL. Within the D2 framework, we prove that pseudo-labels are related to network predictions by an exponential link function, which gives a theoretical support for using predictions as pseudo-labels. Furthermore, we demonstrate that updating pseudo-labels by network predictions will make them uncertain. To mitigate this problem, we propose a training strategy called repetitive reprediction (R2). Finally, the proposed R2-D2 method is tested on the large-scale ImageNet dataset and outperforms state-of-the-art methods by 5 percentage points.

Keywords

Cite

@article{arxiv.2202.08955,
  title  = {R2-D2: Repetitive Reprediction Deep Decipher for Semi-Supervised Deep Learning},
  author = {Guo-Hua Wang and Jianxin Wu},
  journal= {arXiv preprint arXiv:2202.08955},
  year   = {2022}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1908.04345

R2 v1 2026-06-24T09:43:34.969Z