Measure-Based Supervision for Tiny Object Detection in Aerial Imagery
Computers · 22.10.2026 · 15 (11) · 744
DOI: 10.3390/computers15110744 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers, online erschienen am 22.10.2026. Verfasst von Rashid Nasimov und 8 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Detection breaks down on objects a few pixels wide for a structural reason: as box side length shrinks, intersection over union (IoU) degenerates toward an indicator of exact pixel coincidence, so a one-pixel error can rewrite both the label assignment and the regression gradient. We avoid this regime by discarding pairwise box matching altogether. A scene is treated instead as an unnormalized positive measure over object centers, log-scales, and categories, and training minimizes a debiased, uncertainty-aware unbalanced optimal transport divergence between the predicted measure and a Gaussian-smoothed annotation measure. Soft correspondences replace hard assignment, and because the marginals are left free, total confidence mass survives as count supervision. A second training-only signal is drawn from the image itself predicted instances are rendered back to pixels through anisotropic Gaussian footprints, a shared blur kernel, pixel integration, and a capacity limited background, then compared with the observation under a Poisson–Gaussian noise model. Scene priors enter through a clipped log-space gate that caps how far context may suppress appearance evidence, a bound we audit by reporting recall on atypical placements alongside aggregate gains. The method reaches 31.7 AP on the AI-TOD-v2 validation split, including 23.4 AP on 2–8-pixel objects, and 36.8, 37.1, and 31.2 AP on SODA-D, SODA-A, and AI-TOD-R, with 53.6 AP on tiny persons in TinyPerson. Ablations isolate the contribution of each component.
Zitieren
APA
Nasimov, R., Sevinov, J., Abdusalomov, A., Oğurlu, Y., Nosir, N., Abdullaev, A., Kutlimuratov, A., Avazov, K., & Cho, Y. I. (2026). Measure-Based Supervision for Tiny Object Detection in Aerial Imagery. Computers, 15(11), 744. https://doi.org/10.3390/computers15110744
Vancouver
Nasimov R, Sevinov J, Abdusalomov A, Oğurlu Y, Nosir N, Abdullaev A, et al. Measure-Based Supervision for Tiny Object Detection in Aerial Imagery. Computers. 2026;15(11):744. doi:10.3390/computers15110744
BibTeX
@article{Nasimov2026,
author = {Nasimov, Rashid and Sevinov, Jasur and Abdusalomov, Akmalbek and Oğurlu, Yücel and Nosir, Narziev and Abdullaev, Abbosjon and Kutlimuratov, Alpamis and Avazov, Kuldoshbay and Cho, Young Im},
title = {Measure-Based Supervision for Tiny Object Detection in Aerial Imagery},
journal = {Computers},
year = {2026},
volume = {15},
number = {11},
pages = {744},
doi = {10.3390/computers15110744}
}
EUVIMED