Kavli Affiliate: Zhuo Li | First 5 Authors: Zhuo Li, He Zhao, Zhen Li, Tongliang Liu, Dandan Guo | Summary: Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy […]
Continue.. Extracting Clean and Balanced Subset for Noisy Long-tailed Classification