用少量标注数据实现无人机河流地貌视频分割的高精度与时序稳定
Aerial View River Landform Video segmentation: A Weakly Supervised Context-aware Temporal Consistency Distillation Approach
- 采用师生架构+关键帧选择与更新，实现弱监督下的时序一致性蒸馏
- 仅用30%标注数据，mIoU与时序一致性双提升，定位更稳定
- 适合资源受限的航拍地形分析场景，尤其适用于数据标注难的流域监测
通过无人机遥感进行地形与地貌分类的任务，与地面车辆巡检存在显著差异。除面临数据标注复杂、时序一致性难以保证外，还受限于相关数据稀缺及多数技术的有效范围。研究表明，在空中定位任务中，平均交并比（mIoU）和时序一致性（TC）均至关重要。全量标注并非最优方案，仅选取关键帧会削弱时序一致性，导致失败。为此，本文提出一种教师-学生架构，结合关键帧选择与更新算法，实现弱监督学习与时序一致性知识蒸馏，克服传统方法在空中任务中的不足。实验表明，仅使用30%标注数据，本方法即可同时提升mIoU与时序一致性，确保地形目标稳定定位。
原文摘要 · Abstract (English)
The study of terrain and landform classification through UAV remote sensing diverges significantly from ground vehicle patrol tasks. Besides grappling with the complexity of data annotation and ensuring temporal consistency, it also confronts the scarcity of relevant data and the limitations imposed by the effective range of many technologies. This research substantiates that, in aerial positioning tasks, both the mean Intersection over Union (mIoU) and temporal consistency (TC) metrics are of paramount importance. It is demonstrated that fully labeled data is not the optimal choice, as selecting only key data lacks the enhancement in TC, leading to failures. Hence, a teacher-student architecture, coupled with key frame selection and key frame updating algorithms, is proposed. This framework successfully performs weakly supervised learning and TC knowledge distillation, overcoming the deficiencies of traditional TC training in aerial tasks. The experimental results reveal that our method utilizing merely 30\% of labeled data, concurrently elevates mIoU and temporal consistency ensuring stable localization of terrain objects. Result demo : https://gitlab.com/prophet.ai.inc/drone-based-riverbed-inspection
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。