Search Results for author:
Found 1 papers, 0 papers with code
SAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image Classification
Contrastive loss ensures the transferable semantic directions are class-irrelevant and mode seeking loss is adopted to produce diverse tail-class features and enlarge the feature space of tail classes.
Ranked #29 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Cannot find the paper you are looking for? You can
Submit a new open access paper.
