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).

There are 1000 iterations between every two checkpoints. SSL algorithms and the FlexMatch achieves the best accuracy. Our toolbox is partially based on [7]. More importantly, in addition to the basic SSL methods and components, we implement several techniques to make the results stable under PyTorch framework. CIFAR-100, SVHN, and STL-10, and report the best error rates in Table 6, 7, 8, and 9, respectively.

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks.

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks.

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).

This is also the official implementation for FlexMatch: boosting semi-supervised learning using curriculum pseudo labeling published at NeurIPS 2021. TorchSSL is an all-in-one toolkit based on PyTorch for semi-supervised learning (SSL). Currently, we implmented 9 popular SSL algorithms to enable fair comparison and boost the development of SSL algorithms. Besides, we implement our Curriculum Pseudo Labeling (CPL) method for Pseudo-Label (Flex-Pseudo-Label) and UDA (Flex-UDA). The results are best accuracies with standard errors.