Cost-Aware Active Learning Framework for Efficient Small-Object Detection in Agricultural Images
Electronics · 2026-03-13 · 15 (6) · 1196
DOI: 10.3390/electronics15061196 ↗At a glance
Journal article in Electronics, published online on 2026-03-13. Written by Mirjana Bonković and 3 co-authors. Cited 1 times so far (Crossref); 23 references. The full text is freely available (open access, CC BY 4.0). Funded by: Croatian Science Foundation.
Abstract (original language)
Although active learning can reduce the effort required to annotate object detection data, many current methods rely on a single selection criterion or combine criteria without accounting for annotation costs or their interactions. This paper presents a multi-criterion, cost-aware active learning framework for detecting small objects in agricultural images. The framework jointly considers prediction uncertainty, object size, scene density, and annotation cost. We evaluate both scalarized and Pareto-based selection strategies across five cost models and conduct an ablation study to examine the role and interactions of each criterion. Experimental results demonstrate that explicit annotation cost modeling improves active learning efficiency by reducing the amount of annotation required to achieve a given level of detection performance. Across multiple cost formulations and selection strategies, cost-aware acquisition reaches comparable accuracy and reduces the estimated annotation effort required to reach comparable detection performance by up to 50% compared to random sampling, where annotation effort is approximated using prediction-derived cost proxies.
Funding
- Croatian Science Foundation
Cite
APA
Bonković, M., Uvodić, O., Musić, J., & Papić, V. (2026). Cost-Aware Active Learning Framework for Efficient Small-Object Detection in Agricultural Images. Electronics, 15(6), 1196. https://doi.org/10.3390/electronics15061196
Vancouver
Bonković M, Uvodić O, Musić J, Papić V. Cost-Aware Active Learning Framework for Efficient Small-Object Detection in Agricultural Images. Electronics. 2026;15(6):1196. doi:10.3390/electronics15061196
BibTeX
@article{Bonkovi2026,
author = {Bonković, Mirjana and Uvodić, Ozana and Musić, Josip and Papić, Vladan},
title = {Cost-Aware Active Learning Framework for Efficient Small-Object Detection in Agricultural Images},
journal = {Electronics},
year = {2026},
volume = {15},
number = {6},
pages = {1196},
doi = {10.3390/electronics15061196}
}
EUVIMED