Diversity-Enhanced Distribution Alignment for Dataset Distillation

Hongcheng Li, Yucan Zhou, Xiaoyan Gu, Bo Li, Weiping Wang

ICCV 2025 · first public 2025-10

paper ↗catalogued✓ abstract read

In one paragraph

Matches both class-wise means and covariance matrices of pretrained-model features between real and synthetic data in a Gaussian-distribution-alignment scheme, then adds a regularizer that maximizes diagonal and minimizes off-diagonal covariance terms in the last feature layer specifically, countering the low diversity and gradient starvation that mean/BN-statistics-only alignment produces; reports state-of-the-art results on CIFAR-10/100, Tiny-ImageNet and ImageNet-1K with no added compute.

Where it sits

Distribution and feature matching (Surrogate matching)
Setting: Image classification

Builds on

BibTeX (generated; prefer the venue's official entry)

@article{li2025diversity,
  title   = {Diversity-Enhanced Distribution Alignment for Dataset Distillation},
  author  = {Hongcheng Li and Yucan Zhou and Xiaoyan Gu and Bo Li and Weiping Wang},
  journal = {ICCV 2025},
  year    = {2025}
}

Nearby in Distribution and feature matching

2026-06

RAHA — Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon · ECCV 2026notableVision–language paper ↗code ↗

2026-05

MDM — Multimodal Distribution Matching for Vision-Language Dataset Distillation

Jongoh Jeong, Hoyong Kwon, Minseok Kim et al. · CVPR 2026notableVision–language paper ↗code ↗

2026-03

Sneakdoor — SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

He Yang, Dongyi Lv, Song Ma et al. · NeurIPS 2025notablepaper ↗code ↗

2026-03

Harmonic Dataset Distillation for Time Series Forecasting

Seungha Hong, Sanghwan Jang, Wonbin Kweon et al. · AAAI 2026notableTime series paper ↗

2025-11

Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets

Aaryan Gupta, Rishi Saket, Aravindan Raghuveer · ICLR 2026notableOther data paper ↗