Metraipolis › archive › dc_ad79585fd78c
Data-Efficient Classifier Pretraining Through Diffusion Models — arXiv:2610.23289
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23289
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:48:42.522Z
- SHA-256 of the archived text
2e04a9c9489cd589385dbb73b2636dda28b2c80ecc3b6f42e0420e44b12ba0d0- Stable URL of this page
https://metraipolis.com/documento/dc_ad79585fd78c
How to cite
Data-Efficient Classifier Pretraining Through Diffusion Models — arXiv:2610.23289 — arXiv (en), https://arxiv.org/abs/2610.23289 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad79585fd78c (Metraipolis archive dc_ad79585fd78c, sha256 2e04a9c9489cd589385dbb73b2636dda28b2c80ecc3b6f42e0420e44b12ba0d0)
BibTeX
@misc{dcad79585fd78c,
title = {Data-Efficient Classifier Pretraining Through Diffusion Models — arXiv:2610.23289},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23289},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad79585fd78c; sha256 2e04a9c9489cd589385dbb73b2636dda28b2c80ecc3b6f42e0420e44b12ba0d0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23289. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine learning with limited data is susceptible to overfitting, especially with modern deep neural networks. Prior to the introduction of AlexNet, reconstruction-based pretraining with auto-encoder and denoising auto-encoder were found to be beneficial, partially due to the limited size of the training sets at the time. Motivated by these traditional approaches, we propose DiffPT, a simple diffusion modeling approach to pretrain a given classifier backbone for limited domain-specific training data. We experiment on time-series data, standard natural-image benchmarks, and medical imaging datasets, and contrast the diffusion approach to a multitude of modern and traditional un/self-supervised methods. While contrastive pretraining performs better on CIFAR-10 and Tiny ImageNet in low-data regimes, DiffPT is particularly effective on medical imaging and time-series tasks, where it outperforms self-supervised baselines across a range of low-data regimes. Our results suggest that DiffPT is a simple and effective approach for data-efficient classifier pretraining on different modalities. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.23289 — 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 2026-10-19T08:42:40.271Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).