Semantic Consistency and Uncertainty-Driven Small-Object Detection for Class Imbalance.
Saved in:
| Title: | Semantic Consistency and Uncertainty-Driven Small-Object Detection for Class Imbalance. |
|---|---|
| Authors: | Chen, Nuo1 (AUTHOR), Zhao, Peng1 (AUTHOR) zpxhh@163.com, Hou, Shouquan1 (AUTHOR) |
| Source: | Remote Sensing. Jul2026, Vol. 18 Issue 13, p2208. 21p. |
| Subjects: | Remote sensing, Resampling (Statistics), Drone aircraft, Object recognition (Computer vision), Contrastive learning |
| Abstract: | Highlights: What are the main findings? This study proposes a semantic consistency and uncertainty-driven training framework, named SCUD, to address class imbalance in UAV aerial small-object detection. The proposed method improves detection performance on both the DOTA-v1.0 and DIOR datasets, achieving mAP50 values of 70.7% and 88.1%, respectively, with notable improvements for rare categories and small-scale targets. What are the implications of the main findings? The proposed framework provides an effective solution for improving detection robustness in class-imbalanced remote sensing scenarios. By jointly considering feature consistency, scale-aware resampling, and uncertainty-driven instance selection, the method can reduce missed detections and improve the practical applicability of aerial image object detection. In aerial image small-object detection, complex imaging perspectives, arbitrary object orientations, and long-tailed category distributions jointly exacerbate sample imbalance, which significantly degrades detection stability and leads to frequent misclassification of minority categories. To address these challenges, this paper proposes a novel training framework termed SCUD. Specifically, in the label noise suppression strategy (LNSS), a contrastive learning mechanism based on semantic consistency is introduced to constrain the aggregation of similar samples in the feature space, thereby reducing the adverse impact of noisy samples on model optimization. In addition, a scale-aware resampling strategy (SARS) is designed to alleviate noise amplification and overfitting caused by excessive repetition of small objects during training. Furthermore, an adaptive instance selection mechanism (AISM) is developed by jointly modeling prediction uncertainty and global statistical priors, enabling the model to dynamically emphasize learning from informative samples. Extensive experiments are conducted on two publicly available unmanned aerial vehicle (UAV) aerial image datasets to validate the effectiveness of the proposed approach. The proposed method achieves an mAP50 of 70.7% on the DOTA-v1.0 dataset and 88.1% on the DIOR dataset. Notably, the detection accuracy of several rare categories is significantly improved, further demonstrating the effectiveness of the proposed method in addressing sample imbalance in aerial image small-object detection. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? This study proposes a semantic consistency and uncertainty-driven training framework, named SCUD, to address class imbalance in UAV aerial small-object detection. The proposed method improves detection performance on both the DOTA-v1.0 and DIOR datasets, achieving mAP50 values of 70.7% and 88.1%, respectively, with notable improvements for rare categories and small-scale targets. What are the implications of the main findings? The proposed framework provides an effective solution for improving detection robustness in class-imbalanced remote sensing scenarios. By jointly considering feature consistency, scale-aware resampling, and uncertainty-driven instance selection, the method can reduce missed detections and improve the practical applicability of aerial image object detection. In aerial image small-object detection, complex imaging perspectives, arbitrary object orientations, and long-tailed category distributions jointly exacerbate sample imbalance, which significantly degrades detection stability and leads to frequent misclassification of minority categories. To address these challenges, this paper proposes a novel training framework termed SCUD. Specifically, in the label noise suppression strategy (LNSS), a contrastive learning mechanism based on semantic consistency is introduced to constrain the aggregation of similar samples in the feature space, thereby reducing the adverse impact of noisy samples on model optimization. In addition, a scale-aware resampling strategy (SARS) is designed to alleviate noise amplification and overfitting caused by excessive repetition of small objects during training. Furthermore, an adaptive instance selection mechanism (AISM) is developed by jointly modeling prediction uncertainty and global statistical priors, enabling the model to dynamically emphasize learning from informative samples. Extensive experiments are conducted on two publicly available unmanned aerial vehicle (UAV) aerial image datasets to validate the effectiveness of the proposed approach. The proposed method achieves an mAP50 of 70.7% on the DOTA-v1.0 dataset and 88.1% on the DIOR dataset. Notably, the detection accuracy of several rare categories is significantly improved, further demonstrating the effectiveness of the proposed method in addressing sample imbalance in aerial image small-object detection. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18132208 |
