Metraipolis › archive › dc_b8ffa7943ca8
Geometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning — arXiv:2610.35329
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35329
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:02:39.603Z
- SHA-256 of the archived text
adeb907a8289904ff31263cc21a77b10f0b0298b9132329a2409c13b68418300- Stable URL of this page
https://metraipolis.com/documento/dc_b8ffa7943ca8
How to cite
Geometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning — arXiv:2610.35329 — arXiv (en), https://arxiv.org/abs/2610.35329 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8ffa7943ca8 (Metraipolis archive dc_b8ffa7943ca8, sha256 adeb907a8289904ff31263cc21a77b10f0b0298b9132329a2409c13b68418300)
BibTeX
@misc{dcb8ffa7943ca8,
title = {Geometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning — arXiv:2610.35329},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35329},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8ffa7943ca8; sha256 adeb907a8289904ff31263cc21a77b10f0b0298b9132329a2409c13b68418300},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35329. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio active learning (AL) trains a classifier at low annotation cost by labeling only an informative fraction of an unlabeled collection over successive rounds. Each round picks one of the checkpoints saved during training. Mainstream AL protocols do so with an assumed validation set, but in practice its labels also count toward the annotation cost, shrinking the advantage of an already small annotation budget. We propose geometric consistency, a label-free validation rule for checkpoint selection. Both classifiers, nearest-class-mean and k-nearest-neighbor, are built from the labeled set in a frozen pretrained embedding space. They then predict the unlabeled data to model its geometry. The rule scores each checkpoint by its agreement with these pseudo-labels and its cross-entropy on the labeled set. It works with any query strategy, has one hyperparameter, insensitive in practice, and adds only one batched forward pass over the unlabeled data per round. At matched label budgets across datasets, encoders, and query strategies, it attains the best mean rank in area under the labeling curve (AULC) among methods without extra labels and is on par with an out-of-budget validation set. To our knowledge, this is the first systematic study of label-free validation for checkpoint selection in audio AL. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.35329 — 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 2026-10-27T07:55:30.983Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).