Metraipolis › archive › dc_4736b4fa4497
PSM: Dataset Distillation Based on Precise Statistical Matching by Difficulty — arXiv:2609.34299
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34299
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:52:02.707Z
- SHA-256 of the archived text
16cbdcaad3289423d9a0eb9657fc424c1ec3ad42a7d63758414b2a3de0b7b185- Stable URL of this page
https://metraipolis.com/documento/dc_4736b4fa4497
How to cite
PSM: Dataset Distillation Based on Precise Statistical Matching by Difficulty — arXiv:2609.34299 — arXiv (en), https://arxiv.org/abs/2609.34299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4736b4fa4497 (Metraipolis archive dc_4736b4fa4497, sha256 16cbdcaad3289423d9a0eb9657fc424c1ec3ad42a7d63758414b2a3de0b7b185)
BibTeX
@misc{dc4736b4fa4497,
title = {PSM: Dataset Distillation Based on Precise Statistical Matching by Difficulty — arXiv:2609.34299},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34299},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4736b4fa4497; sha256 16cbdcaad3289423d9a0eb9657fc424c1ec3ad42a7d63758414b2a3de0b7b185},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dataset distillation (DD) condenses a large original dataset into a small distilled dataset with high training utility. Decoupled statistical matching methods substantially reduce distillation time and memory overhead while achieving strong performance. However, they typically supervise all distilled samples using running statistics estimated from the entire original dataset. These statistics mainly capture the average feature distribution while overlooking differences in sample difficulty, limiting their ability to characterize the difficulty structure of the original data. To address this issue, we propose Precise Statistical Matching (PSM) by difficulty. After pretraining, PSM uses the Global Precision Score (GPS) to estimate image difficulty, ranks the samples within each class, and partitions each class into IPC (images per class) difficulty groups. During distillation, Statistics Updated Again (SUA) updates the teacher's batch normalization (BN) running statistics through forward passes on original samples from each group, providing difficulty-specific supervision for the corresponding distilled batch. Meanwhile, Initial Sample Screening (ISS) initializes distilled samples using original images from the corresponding difficulty group, providing an effective starting point for precise matching. Experiments across multiple datasets and model architectures demonstrate that PSM broadens the difficulty range of distilled samples and improves downstream performance in most evaluated settings. Code will be released. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34299 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T23:29:27.342Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).