Measure-Based Supervision for Tiny Object Detection in Aerial Imagery
Year: 2026
Type: article
Abstract: 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.
Source: Computers
Institutions: Gachon University, Tashkent State Technical University named after Islam Karimov, University of Tashkent for Applied Sciences, Balıkesir University, Tashkent University of Information Technology, Alfraganus University, Tashkent State University of Economics, Fergana State Technical University, Kimyo International University in Tashkent, Samarkand State University named after Sharof Rashidov
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,172
OpenAlex ID: W7223264282
