×

FlexMatch

swMATH ID: 43050
Software Authors: Zhang, Bowen; Wang, Yidong; Hou, Wenxin; Wu, Hao; Wang, Jindong; Okumura, Manabu; Shinozaki, Takahiro
Description: FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling. 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
Homepage: https://arxiv.org/abs/2110.08263
Source Code:  https://github.com/TorchSSL/TorchSSL
Dependencies: Python
Keywords: Machine Learning; arXiv_cs.LG; Computer Vision; Pattern Recognition; arXiv_cs.CV; FlexMatch; Boosting; Semi-Supervised Learning; Curriculum Pseudo Labeling
Related Software: MixMatch; Python; FixMatch; PyTorch; ReMixMatch; S4L; LAMDA-SSL; Scikit; SemiBoost; SGDR; RandAugment; ImageNet; CIFAR
Cited in: 0 Documents

Standard Articles

1 Publication describing the Software Year
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling arXiv
Bowen Zhang, Yidong Wang, Wenxin Hou, Hao Wu, Jindong Wang, Manabu Okumura, Takahiro Shinozaki
2021