CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation

Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training data. Existing DFKD methods focus primarily on improving image recognition performance on associated datasets, often negle...

Full description

Bibliographic Details

Published in:	2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors:	Zhang, Zherui, Wang, Changwei, Xu, Rongtao, Xu, Wenhao, Xu, Shibiao, Zhang, Yu, Zhou, Jie, Guo, Li
Format:	Conference Proceeding
Language:	English
Published:	IEEE 22.06.2025
Subjects:	Contrastive learning Design automation Generators Image recognition Knowledge Distillation Knowledge engineering Knowledge transfer Representation learning Training Training data Transfer learning
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!