Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
Open paper
Benchmark
Model
Rank
Results
long-tail-learning-on-cifar-10-lt-r-10
Causal Norm
#30
Error Rate: 11.5
long-tail-learning-on-cifar-10-lt-r-10
DecTDE
#36
Error Rate: 12.63
long-tail-learning-on-imagenet-lt
De-confound-TDE
#48
Top-1 Accuracy: 51.8
Rank counts only results with a code link.