Metraipolis › archive › dc_722cde4f57ce

OT-CAL: Optimal-Transport-Guided Adaptive Sample Selection for Efficient Visual Learning — arXiv:2610.41677

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41677
License (as archived)
CC0-1.0
Archived
2026-11-03T05:33:33.174Z
SHA-256 of the archived text
b1ce754ab08940999d4cb05429101e934d6114810374ab8f52ee33da630f24b0
Stable URL of this page
https://metraipolis.com/documento/dc_722cde4f57ce

How to cite

OT-CAL: Optimal-Transport-Guided Adaptive Sample Selection for Efficient Visual Learning — arXiv:2610.41677 — arXiv (en), https://arxiv.org/abs/2610.41677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_722cde4f57ce (Metraipolis archive dc_722cde4f57ce, sha256 b1ce754ab08940999d4cb05429101e934d6114810374ab8f52ee33da630f24b0)
BibTeX
@misc{dc722cde4f57ce,
  title = {OT-CAL: Optimal-Transport-Guided Adaptive Sample Selection for Efficient Visual Learning — arXiv:2610.41677},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41677},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_722cde4f57ce; sha256 b1ce754ab08940999d4cb05429101e934d6114810374ab8f52ee33da630f24b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep neural networks for image recognition are typically trained using mini-batches, with a forward pass to compute predictions and losses followed by a more computationally expensive backward pass to update model parameters. However, not all training samples contribute equally to learning, suggesting that computation can be reduced by performing backward passes only on informative samples. The challenge is that sample informativeness changes throughout training: difficult samples may be valuable early on, improving samples become important later, and class diversity becomes increasingly relevant toward the end. Existing methods often rely on fixed selection rules or computationally expensive per-sample gradient calculations. We propose OT-CAL, an adaptive data selection method that automatically adjusts its sampling preferences during training. OT-CAL represents each sample using five informativeness features, including difficulty, learnability, and uncertainty. A curriculum vector describes the currently preferred sample characteristics, and optimal-transport-based matching assigns selection weights according to how closely samples match this target. The curriculum vector is then updated using the selected samples, forming a feedback loop that adapts without a manually defined schedule. Experiments on three standard visual learning benchmarks show that, when selecting 50% of each mini-batch, OT-CAL improves performance by 1.3--2.1 points over AdaSelection while achieving 1.18--1.24 times faster training than full-data training.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41677 — 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 2026-11-03T05:18:52.224Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).