Kavli Affiliate: Zheng Zhu | First 5 Authors: Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Shuo Yang | Summary: Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the […]
Continue.. CAFE: Learning to Condense Dataset by Aligning Features