EUVIMEDEUVIMED entdecken
Crossref

Dataset Distillation with ControlNet for Fine‐Grained Classification

Minhao Li, Yawen Zou, Chao Zhang, Haoran Xie

IEEJ Transactions on Electrical and Electronic Engineering · 28.04.2026

DOI: 10.1002/tee.70316 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEJ Transactions on Electrical and Electronic Engineering, online erschienen am 28.04.2026. Verfasst von Minhao Li und 3 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: Japan Science and Technology Agency.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dataset distillation aims to condense large‐scale datasets into smaller synthetic ones, enabling efficient training with lower storage and computational costs while achieving performance comparable to models trained on the full dataset. Despite notable successes, existing methods often struggle on fine‐grained tasks due to the subtle and complex inter‐class differences inherent in such datasets. To address this challenge, we propose a ControlNet‐enhanced distillation framework that synthesizes high‐quality images with rich fine‐grained details. Specifically, we utilize synthetic images produced by existing distillation methods as supervision signals within a conditional diffusion model guided by ControlNet. To ensure diversity and representativeness, the dataset is partitioned and clustered to construct representative subsets for training and synthesis. ControlNet is fine‐tuned on the training subset using prior knowledge from external synthetic images, and subsequently used to generate high‐resolution images under the guidance of control inputs from the synthesis subset. Experimental results on multiple fine‐grained datasets demonstrate that our method generates diverse, detail‐rich images and achieves state‐of‐the‐art performance. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Förderung

  • Japan Science and Technology Agency

Zitieren

APA

Li, M., Zou, Y., Zhang, C., & Xie, H. (2026). Dataset Distillation with ControlNet for Fine‐Grained Classification. IEEJ Transactions on Electrical and Electronic Engineering. https://doi.org/10.1002/tee.70316

Vancouver

Li M, Zou Y, Zhang C, Xie H. Dataset Distillation with ControlNet for Fine‐Grained Classification. IEEJ Transactions on Electrical and Electronic Engineering. 2026. doi:10.1002/tee.70316

BibTeX
@article{Li2026,
  author = {Li, Minhao and Zou, Yawen and Zhang, Chao and Xie, Haoran},
  title = {Dataset Distillation with ControlNet for Fine‐Grained Classification},
  journal = {IEEJ Transactions on Electrical and Electronic Engineering},
  year = {2026},
  doi = {10.1002/tee.70316}
}
Kostenlos starten →