To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T).
To achieve joint channel estimation and feedback, this paper proposes an encoder-decoder based network that unveils the intrinsic frequency-domain correlation within the CSI matrix.
It is unfavorable for training on balanced data, but can be utilized to adjust the validity of the samples in long-tailed data, thereby solving the distorted embedding space of long-tailed problems.
Ranked #11 on Long-tail Learning on CIFAR-10-LT (ρ=100)
Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a biased model.
Ranked #12 on Long-tail Learning on CIFAR-10-LT (ρ=100)
Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead.
To address this problem, state-of-the-art methods usually adopt a mixture of experts (MoE) to focus on different parts of the long-tailed distribution.
1 code implementation • • Mingjie Li, Wenjia Cai, Rui Liu, Yuetian Weng, Xiaoyun Zhao, Cong Wang, Xin Chen, Zhong Liu, Caineng Pan, Mengke Li, Yizhi Liu, Flora D Salim, Karin Verspoor, Xiaodan Liang, Xiaojun Chang
Researchers have explored advanced methods from computer vision and natural language processing to incorporate medical domain knowledge for the generation of readable medical reports.