EUVIMEDEUVIMED entdecken
Crossref

M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy

Hansong Zhang, Shikun Li, Pengju Wang, Dan Zeng, Shiming Ge

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (8) · 9314-9322

DOI: 10.1609/aaai.v38i8.28784 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Hansong Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Training state-of-the-art (SOTA) deep models often requires extensive data, resulting in substantial training and storage costs. To address these challenges, dataset condensation has been developed to learn a small synthetic set that preserves essential information from the original large-scale dataset. Nowadays, optimization-oriented methods have been the primary method in the field of dataset condensation for achieving SOTA results. However, the bi-level optimization process hinders the practical application of such methods to realistic and larger datasets. To enhance condensation efficiency, previous works proposed Distribution-Matching (DM) as an alternative, which significantly reduces the condensation cost. Nonetheless, current DM-based methods still yield less comparable results to SOTA optimization-oriented methods. In this paper, we argue that existing DM-based methods overlook the higher-order alignment of the distributions, which may lead to sub-optimal matching results. Inspired by this, we present a novel DM-based method named M3D for dataset condensation by Minimizing the Maximum Mean Discrepancy between feature representations of the synthetic and real images. By embedding their distributions in a reproducing kernel Hilbert space, we align all orders of moments of the distributions of real and synthetic images, resulting in a more generalized condensed set. Notably, our method even surpasses the SOTA optimization-oriented method IDC on the high-resolution ImageNet dataset. Extensive analysis is conducted to verify the effectiveness of the proposed method. Source codes are available at https://github.com/Hansong-Zhang/M3D.

Zitieren

APA

Zhang, H., Li, S., Wang, P., Zeng, D., & Ge, S. (2024). M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 9314-9322. https://doi.org/10.1609/aaai.v38i8.28784

Vancouver

Zhang H, Li S, Wang P, Zeng D, Ge S. M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(8):9314-9322. doi:10.1609/aaai.v38i8.28784

BibTeX
@article{Zhang2024,
  author = {Zhang, Hansong and Li, Shikun and Wang, Pengju and Zeng, Dan and Ge, Shiming},
  title = {M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {8},
  pages = {9314--9322},
  doi = {10.1609/aaai.v38i8.28784}
}
Kostenlos starten →