no code implementations • 9 Mar 2024 • QiHao Zhao, Yalun Dai, Hao Li, Wei Hu, Fan Zhang, Jun Liu
Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories.
1 code implementation • ICCV 2023 • QiHao Zhao, Chen Jiang, Wei Hu, Fan Zhang, Jun Liu
In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy.
Ranked #5 on Long-tail Learning on CIFAR-10-LT (ρ=50)
1 code implementation • 24 Apr 2023 • QiHao Zhao, Yangyu Huang, Wei Hu, Fan Zhang, Jun Liu
TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model.
Ranked #1 on Data Augmentation on ImageNet
1 code implementation • 14 Sep 2020 • Wei Hu, QiHao Zhao, Yangyu Huang, Fan Zhang
Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability.