CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915267387326464 |
|---|---|
| author | Zhang, Zherui Wang, Changwei Xu, Rongtao Xu, Wenhao Xu, Shibiao Zhang, Yu Guo, Li |
| author_facet | Zhang, Zherui Wang, Changwei Xu, Rongtao Xu, Wenhao Xu, Shibiao Zhang, Yu Guo, Li |
| contents | 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 neglecting the crucial aspect of the transferability of learned representations. In this paper, we propose Category-Aware Embedding Data-Free Knowledge Distillation (CAE-DFKD), which addresses at the embedding level the limitations of previous rely on image-level methods to improve model generalization but fail when directly applied to DFKD. The superiority and flexibility of CAE-DFKD are extensively evaluated, including: \textit{\textbf{i.)}} Significant efficiency advantages resulting from altering the generator training paradigm; \textit{\textbf{ii.)}} Competitive performance with existing DFKD state-of-the-art methods on image recognition tasks; \textit{\textbf{iii.)}} Remarkable transferability of data-free learned representations demonstrated in downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21478 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation Zhang, Zherui Wang, Changwei Xu, Rongtao Xu, Wenhao Xu, Shibiao Zhang, Yu Guo, Li Computer Vision and Pattern Recognition Neural and Evolutionary Computing 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 neglecting the crucial aspect of the transferability of learned representations. In this paper, we propose Category-Aware Embedding Data-Free Knowledge Distillation (CAE-DFKD), which addresses at the embedding level the limitations of previous rely on image-level methods to improve model generalization but fail when directly applied to DFKD. The superiority and flexibility of CAE-DFKD are extensively evaluated, including: \textit{\textbf{i.)}} Significant efficiency advantages resulting from altering the generator training paradigm; \textit{\textbf{ii.)}} Competitive performance with existing DFKD state-of-the-art methods on image recognition tasks; \textit{\textbf{iii.)}} Remarkable transferability of data-free learned representations demonstrated in downstream tasks. |
| title | CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation |
| topic | Computer Vision and Pattern Recognition Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2504.21478 |