Gongfan Fang

activity

20192026

most citedData-Free Adversarial Distillation

103 citations · 278 across the 43 of their papers we have counts for

collaborators

Showing 2021Show all

3 papers · 1 filter

math.GR2021

A further generalization of the Glauberman-Thompson $p$ -nilpotency criterion in fusion systems

Zhencai Shen, Baoyu Zhang

Let $p$ be a prime and $F$ be a saturated fusion system over a finite $p$ -group $P$ . The fusion system $F$ is said to be nilpotent if $\mathcal{F}=\mathcal{F}_{…

cs.LG2021★ 7 cited

Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

Gongfan Fang, Yifan Bao, Jie Song +4

Knowledge distillation~(KD) aims to craft a compact student model that imitates the behavior of a pre-trained teacher in a target domain. Prior KD approaches, despite their gratify…

cs.AI2021★ 31 cited

Contrastive Model Inversion for Data-Free Knowledge Distillation

Gongfan Fang, Jie Song, Xinchao Wang +3

Model inversion, whose goal is to recover training data from a pre-trained model, has been recently proved feasible. However, existing inversion methods usually suffer from the mod…

A further generalization of the Glauberman-Thompson p-nilpotency criterion in fusion systems

Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

Contrastive Model Inversion for Data-Free Knowledge Distillation

A further generalization of the Glauberman-Thompson $p$ -nilpotency criterion in fusion systems