Appendix: FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling Bowen Zhang

Neural Information Processing Systems 

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.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found