EUVIMEDEUVIMED entdecken
Crossref

Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning

Chang Xu, Ruixiang Zhang, Wen Yang, Haoran Zhu, Fang Xu, Jian Ding, Gui-Song Xia

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-03 · 48 (3) · 3167-3184

DOI: 10.1109/tpami.2025.3634161 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-03. Verfasst von Chang Xu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 94 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting oriented tiny objects, which are limited in appearance information yet prevalent in real-world applications, remains an intricate and under-explored problem. To address this, we systematically introduce a new dataset, a benchmark, and a dynamic coarse-to-fine learning scheme in this study. Our proposed dataset, AI-TOD-R, features the smallest object sizes among all oriented object detection datasets. Based on AI-TOD-R, we present a benchmark spanning a broad range of detection paradigms, including both fully-supervised and label-efficient approaches. Through investigation, we identify a learning bias presents across various learning pipelines: confident objects become increasingly confident, while vulnerable oriented tiny objects are further marginalized, hindering their detection performance. To mitigate this issue, we propose a Dynamic Coarse-to-Fine Learning (DCFL) scheme towards unbiased learning. DCFL dynamically updates prior positions to better align with the limited areas of oriented tiny objects, and it assigns samples in a way that balances both quantity and quality across different object shapes, thus mitigating biases in prior settings and sample selection. Extensive experiments across 10 challenging object detection datasets demonstrate that DCFL achieves state-of-the-art accuracy, high efficiency, and remarkable versatility.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Xu, C., Zhang, R., Yang, W., Zhu, H., Xu, F., Ding, J., & Xia, G. S. (2026). Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(3), 3167-3184. https://doi.org/10.1109/tpami.2025.3634161

Vancouver

Xu C, Zhang R, Yang W, Zhu H, Xu F, Ding J, et al. Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(3):3167-3184. doi:10.1109/tpami.2025.3634161

BibTeX
@article{Xu2026,
  author = {Xu, Chang and Zhang, Ruixiang and Yang, Wen and Zhu, Haoran and Xu, Fang and Ding, Jian and Xia, Gui-Song},
  title = {Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {3},
  pages = {3167--3184},
  doi = {10.1109/tpami.2025.3634161}
}
Kostenlos starten →