Metraipolis › archive › dc_c175e01ac889

Quantifying Annotation Agreement in Object Detection with Optimal Transport — arXiv:2610.19912

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19912
License (as archived): CC0-1.0
Archived: 2026-10-15T21:56:47.539Z
SHA-256 of the archived text: 09b816bea501ca4546d9e58c17d2d417862db2465c024d481f9b2a8c848c84db
Stable URL of this page: https://metraipolis.com/documento/dc_c175e01ac889

How to cite

Quantifying Annotation Agreement in Object Detection with Optimal Transport — arXiv:2610.19912 — arXiv (en), https://arxiv.org/abs/2610.19912 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c175e01ac889 (Metraipolis archive dc_c175e01ac889, sha256 09b816bea501ca4546d9e58c17d2d417862db2465c024d481f9b2a8c848c84db)

BibTeX

@misc{dcc175e01ac889,
  title = {Quantifying Annotation Agreement in Object Detection with Optimal Transport — arXiv:2610.19912},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19912},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c175e01ac889; sha256 09b816bea501ca4546d9e58c17d2d417862db2465c024d481f9b2a8c848c84db},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19912. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable validation of machine learning models is a crucial step in designing robust and trustworthy systems. Yet validation relies on annotated test sets treated as ground truth, even though annotations can be noisy or ambiguous. In object detection, sources may disagree on object presence, box location, or class label. Standard agreement metrics usually binarize box overlap before computing a summary score, obscuring the degree and structure of disagreement between annotation sets. Here, we study an Optimal Transport (OT)-based metric for measuring agreement between object detection annotations. Instead of binarizing bounding box overlap, this metric assigns graded costs to matched and unmatched labeled boxes. Through theoretical analysis and experiments on real and synthetically perturbed annotations, we show that OT captures graded changes in agreement and distinguishes annotation pairs that thresholded metrics score identically. Our results suggest that OT provides a richer measure of annotation agreement in object detection, especially for domains with many small or ambiguous objects. Such agreement estimates can support more reliable validation when labels are noisy or conflicting.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.19912 — 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 2026-10-15T21:38:29.511Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).