FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling

TL;DR

FlexMatch introduces Curriculum Pseudo Labeling to adaptively select unlabeled data based on the model's learning progress, significantly improving semi-supervised learning performance and convergence speed over FixMatch.

Contribution

The paper proposes Curriculum Pseudo Labeling, a novel threshold adjustment method that enhances FixMatch by considering class-specific learning status without extra computational costs.

Findings

FlexMatch outperforms FixMatch on multiple SSL benchmarks.

FlexMatch reduces error rates by up to 19% with limited labels.

CPL accelerates training, achieving better results in one-fifth of the training time.

Abstract

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks. However, like other modern SSL algorithms, FixMatch uses a pre-defined constant threshold for all classes to select unlabeled data that contribute to the training, thus failing to consider different learning status and learning difficulties of different classes. To address this issue, we propose Curriculum Pseudo Labeling (CPL), a curriculum learning approach to leverage unlabeled data according to the model's learning status. The core of CPL is to flexibly adjust thresholds for different classes at each time step to let pass informative unlabeled data and their pseudo labels. CPL does not introduce additional parameters or computations (forward or backward propagation). We apply CPL to FixMatch and call our improved algorithm FlexMatch. FlexMatch achieves state-of-the-art performance on a variety of SSL benchmarks, with especially strong performances when the labeled data are extremely limited or when the task is challenging. For example, FlexMatch achieves 13.96% and 18.96% error rate reduction over FixMatch on CIFAR-100 and STL-10 datasets respectively, when there are only 4 labels per class. CPL also significantly boosts the convergence speed, e.g., FlexMatch can use only 1/5 training time of FixMatch to achieve even better performance. Furthermore, we show that CPL can be easily adapted to other SSL algorithms and remarkably improve their performances. We open-source our code at https://github.com/TorchSSL/TorchSSL.