Sampling to Distill: Knowledge Transfer from Open-World Data

CoRR(2023)

引用 0|浏览38
暂无评分
摘要
Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the teacher network without original training data. Despite encouraging results, existing DFKD methods rely heavily on generation modules with high computational costs. Meanwhile, they ignore the fact that the generated and original data exist domain shifts due to the lack of supervision information. Moreover, knowledge is transferred through each example, ignoring the implicit relationship among multiple examples. To this end, we propose a novel Open-world Data Sampling Distillation (ODSD) method without a redundant generation process. First, we try to sample open-world data close to the original data's distribution by an adaptive sampling module. Then, we introduce a low-noise representation to alleviate the domain shifts and build a structured relationship of multiple data examples to exploit data knowledge. Extensive experiments on CIFAR-10, CIFAR-100, NYUv2, and ImageNet show that our ODSD method achieves state-of-the-art performance. Especially, we improve 1.50\%-9.59\% accuracy on the ImageNet dataset compared with the existing results.
更多
查看译文
关键词
knowledge transfer,distill,data,open-world
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要