A Realistic Instance-Level Data Augmentation Method for Small-Object Detection Based on Scene Understanding
Remote Sensing · 20.02.2026 · 18 (4) · 647
DOI: 10.3390/rs18040647 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 20.02.2026. Verfasst von Chuwei Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic Research Foundation of National Key Laboratory of Automatic Target Recognition.
Abstract (Originalsprache)
Instance-level data augmentation methods, exemplified by “copy-paste”, serve as a conventional strategy for improving the performance of small object detectors. The core idea involves leveraging background redundancy by compositing object instances with suitable backgrounds—drawn either from the same image or from different images—to increase both the quantity and diversity of training samples. However, existing methods often struggle with mismatches in background, scale, illumination, and viewpoint between instances and backgrounds. More critically, their predominant reliance on background information, without a joint understanding of instance-background characteristics, results in augmented images lacking visual realism. Empirical studies have demonstrated that such unrealistic images not only fail to improve detection performance but can even be detrimental. To tackle this problem, we propose a scene-understanding-driven approach that systematically addresses these mismatches via joint instance-background understanding. This is achieved through a unified framework that integrates image inpainting, image tagging, open-set object detection, the Segment Anything Model (SAM), and pose estimation to jointly model instance attributes, background semantics, and their interrelationships, thereby abandoning the random operation paradigm of existing methods and synthesizing highly realistic augmented images while preserving data diversity. On the VisDrone dataset, our method improves the mAP@0.5:0.95 and mAP@0.5 of the baseline detector by 1.6% and 2.2%, respectively. Both quantitative gains and qualitative visualizations confirm that the systematic resolution of these mismatches directly translates into significantly higher visual realism and detection performance improvements.
Förderung
- Basic Research Foundation of National Key Laboratory of Automatic Target Recognition
Zitieren
APA
Li, C., Zhang, Z., Zhong, P., & He, J. (2026). A Realistic Instance-Level Data Augmentation Method for Small-Object Detection Based on Scene Understanding. Remote Sensing, 18(4), 647. https://doi.org/10.3390/rs18040647
Vancouver
Li C, Zhang Z, Zhong P, He J. A Realistic Instance-Level Data Augmentation Method for Small-Object Detection Based on Scene Understanding. Remote Sensing. 2026;18(4):647. doi:10.3390/rs18040647
BibTeX
@article{Li2026,
author = {Li, Chuwei and Zhang, Zhilong and Zhong, Ping and He, Jun},
title = {A Realistic Instance-Level Data Augmentation Method for Small-Object Detection Based on Scene Understanding},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {4},
pages = {647},
doi = {10.3390/rs18040647}
}
EUVIMED