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.
Neural Information Processing Systems
Nov-15-2025, 05:52:04 GMT
- Technology: