Comparison of the classification performance with ABC backbone-based methods on Small-ImageNet-127. (Three random trails and all the results are from our running results). MethodTop1 accuracy RMM 14.95±0.63 w/ ABC 32.40±0.63 w/ ABC+3LPR 33.14±0.65 FixMatch 16.97±0.52 w/ ABC 30.15...
Experiments on benchmark datasets, including CIFAR100, miniImageNet, and CUB200, demonstrate the improved performance of ALICE over the state-of-the-art FSCIL methods.doi:10.48550/arXiv.2208.00147Peng, CanZhao, KunWang, TianrenLi, MengLovell, Brian C....
After RRL, the classification head is refined with global class-balanced classification loss to address the data imbalance issue as well as learn the decision boundaries between new and previous classes. Extensive experiments on CIFAR100, Tiny-ImageNet200, and ImageNet100 demonstrate that our R-DF...