ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot

Open paper

Benchmark	Model	Rank	Results
long-tail-learning-on-cifar-10-lt-r-100	ACE (4 experts)	–	Error Rate: 18.6
long-tail-learning-on-cifar-100-lt-r-100	ACE (4 experts)	–	Error Rate: 50.4