轻量级模型FCBNet高效精准识别多光谱航拍中的杂草。
A Parameter-efficient Convolutional Approach for Weed Detection in Multispectral Aerial Imagery
- 冻结主干网络+轻量化特征修正模块，提升特征表达能力。
- 在两个数据集上mIoU超85%，训练仅需0.06至0.2小时。
- 参数量减少90%以上，适合资源受限的农业场景部署。
我们提出FCBNet，一种用于杂草分割的高效模型。该架构基于完全冻结的ConvNeXt主干网络，结合提出的特征修正模块（FCB），利用高效卷积进行特征精炼，并配备轻量级解码器。FCBNet在WeedBananaCOD和WeedMap数据集上，于RGB与多光谱模态下均进行了评估，其mIoU超过85%，优于U-Net、DeepLabV3+、SK-U-Net、SegFormer及WeedSense等模型。同时，其训练时间仅为0.06至0.2小时，具有优异的计算效率。冻结主干策略使可训练参数减少超90%，显著降低内存需求。
原文摘要 · Abstract (English)
We introduce FCBNet, an efficient model designed for weed segmentation. The architecture is based on a fully frozen ConvNeXt backbone, the proposed Feature Correction Block (FCB), which leverages efficient convolutions for feature refinement, and a lightweight decoder. FCBNet is evaluated on the WeedBananaCOD and WeedMap datasets under both RGB and multispectral modalities, showing that FCBNet outperforms models such as U-Net, DeepLabV3+, SK-U-Net, SegFormer, and WeedSense in terms of mIoU, exceeding 85%, while also achieving superior computational efficiency, requiring only 0.06 to 0.2 hours for training. Furthermore, the frozen backbone strategy reduces the number of trainable parameters by more than 90%, significantly lowering memory requirements.
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。