real-world data are long-tailed, the lack of tail samples leads to a
significant limitation in the generalization ability of the model. Although
numerous approaches of class re-balancing perform well for moderate
本文研究如何学习 deep learning 中的 feature 并解决长尾数据集中头尾类别分布错位、影响特征判别能力的问题。我们提出了使用‘特征云’方法来恢复长尾数据集的‘类内多样性’,并在 person re-identification 和 face recognition 任务中进行实验验证。