用少量实地数据低成本适配农业机器人视觉模型，提升田间检测精度。
From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots
- 从网络数据到实地数据的无监督域适应，减少现场标注成本。
- 引入多级注意力对抗判别器，使检测模型在新田地准确率提升7.5%。
- 适用于需快速部署的农业机器人，尤其适合资源有限的场景。
在精准农业中，视觉模型常因作物与杂草受外部因素影响，在新田地中出现与训练分布不同的外观和组成，导致性能下降。本文提出一种低成本无监督域适应方法，利用互联网海量数据与少量机器人实地采集数据进行域迁移，减少对大量现场数据的需求。我们设计了多级注意力对抗判别器（MAAD），可嵌入任意检测模型的特征提取层。本研究将MAAD与CenterNet结合，实现对叶片、茎秆和叶脉实例的联合检测。实验表明，相比基线模型，目标域中的物体检测准确率提升7.5%，关键点检测性能提高5.1%。
原文摘要 · Abstract (English)
In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appearances that differ from the learned distribution. This paper aims to adapt to specific fields at low cost using Unsupervised Domain Adaptation (UDA). We explore a novel domain shift from a diverse, large pool of internet-sourced data to a small set of data collected by a robot at specific locations, minimizing the need for extensive on-field data collection. Additionally, we introduce a novel module -- the Multi-level Attention-based Adversarial Discriminator (MAAD) -- which can be integrated at the feature extractor level of any detection model. In this study, we incorporate MAAD with CenterNet to simultaneously detect leaf, stem, and vein instances. Our results show significant performance improvements in the unlabeled target domain compared to baseline models, with a 7.5% increase in object detection accuracy and a 5.1% improvement in keypoint detection.
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。