Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
This work addresses a foundational theoretical gap in semi-supervised deep learning, offering a principled framework that could enhance model performance in data-scarce scenarios.
The paper tackled the lack of theoretical justification for using network predictions as pseudo-labels in semi-supervised learning by proposing the deep decipher (D2) framework, which proves an exponential link function between predictions and pseudo-labels, and introduced a repetitive reprediction (R2) strategy to reduce uncertainty, resulting in a 5 percentage point improvement over state-of-the-art methods on ImageNet.
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 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.