Metraipolis › archive › dc_d41da91ea6f9

[Re] Pure Noise to the Rescue of Insufficient Data — arXiv:2611.01295

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01295
License (as archived)
CC0-1.0
Archived
2026-11-03T18:40:26.216Z
SHA-256 of the archived text
9a01a6d9f4b6caf06a482da86a780b6e1781b6835bebf0583cff4b70bb2a024e
Stable URL of this page
https://metraipolis.com/documento/dc_d41da91ea6f9

How to cite

[Re] Pure Noise to the Rescue of Insufficient Data — arXiv:2611.01295 — arXiv (en), https://arxiv.org/abs/2611.01295 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d41da91ea6f9 (Metraipolis archive dc_d41da91ea6f9, sha256 9a01a6d9f4b6caf06a482da86a780b6e1781b6835bebf0583cff4b70bb2a024e)
BibTeX
@misc{dcd41da91ea6f9,
  title = {[Re] Pure Noise to the Rescue of Insufficient Data — arXiv:2611.01295},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01295},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d41da91ea6f9; sha256 9a01a6d9f4b6caf06a482da86a780b6e1781b6835bebf0583cff4b70bb2a024e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01295. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We examine the main claims of Zada, Benou, and Irani (2021), which states that in an image classification task with imbalanced training data, (i) using pure noise to augment minority-class images encourages generalization by improving minority-class accuracy. This method is paired with (ii) a new batch normalization layer that normalizes noise images using affine parameters learned from natural images, which improves the model's performance. Moreover, (iii) this improvement is robust to varying levels of data augmentation. Finally, the authors propose that (iv) adding pure noise images can improve classification even on balanced training data. We implemented the training pipeline from the description of the paper using PyTorch and integrated authors' code snippets for sampling pure noise images and batch normalizing noise and natural images separately. We reproduced the main claims that (i) oversampling with pure noise improves generalization by improving the minority-class accuracy, (ii) the proposed batch normalization (BN) method outperforms baselines, (iii) and this improvement is robust across data augmentations. Our results also support that (iv) adding pure noise images can improve classification on balanced training data. However, additional experiments suggest that the performance improvement from OPeN may be more orthogonal to the improvement caused by a bigger network or more complex data augmentation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01295 — 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 2026-11-03T18:12:54.725Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).