BEM: Balanced and Entropy-Based Mix for Long-Tailed Semi-Supervised Learning

Test accuracy gain (%) FixMatch FixMatch+LA FixMatch+ABC FixMatch+ACR (d) Test accuracy gain Figure 1. Experimental results on CIFAR10-LT [24]. (a)-(c): Class distribution of unlabeled data quantity and entropy for three typical settings, which have the same labeled data quantity distribution but differ in unlabeled ones. Both the data quantity and entropy are the statistical averages within one epoch after model convergence. Unexpected discrepancies are observed across all settings between the distribution of data quantity and entropy, particularly for head and tail classes. Notably, classes 3-6 exhibit the highest entropy, indicating greater uncertainty. (d): Test accuracy gain brought by BEM for various LTSSL frameworks in consistent setting.