A Parameter-efficient Convolutional Approach for Camouflaged Weed Detection in Multispectral Aerial Imagery.

arXiv:2603.06655v2 Announce Type: replace-cross Abstract: We introduce FCBNet, an efficient model designed for camouflaged weed detection. The architecture is based on a fully frozen ConvNeXt backbone, the proposed Feature Correction Block (FCB), which leverag