Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation

1 code implementation • 31 Mar 2024 • Wenxiao Deng, Wenbin Li, Tianyu Ding, Lei Wang, Hongguang Zhang, Kuihua Huang, Jing Huo, Yang Gao

However, these methods face two primary limitations: the dispersed feature distribution within the same class in synthetic datasets, reducing class discrimination, and an exclusive focus on mean feature consistency, lacking precision and comprehensiveness.