Papers Long-tail Learning on CIFAR-10-LT (ρ=100)

“Long-tail Learning on CIFAR-10-LT (ρ=100)” 태그가 달린 논문 2편 · 필터 해제

Balanced Contrastive Learning for Long-Tailed Visual Recognition

2022-07-19 · CVPR 2022 7 · Jianggang Zhu, Zheng Wang, Jingjing Chen, Yi-Ping Phoebe Chen 외

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cr…

Contrastive Learning Image Classification Long-tail Learning Long-tail Learning on CIFAR-10-LT (ρ=100)+1

Balanced Product of Calibrated Experts for Long-Tailed Recognition

2022-06-10 · CVPR 2023 1 · Emanuel Sanchez Aimar, Arvi Jonnarth, Michael Felsberg, Marco Kuhlmann

Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging due to limited generalization over the tail classes. If the t…

Long-tail Learning Long-tail Learning on CIFAR-10-LT (ρ=100)Representation Learning