A3UNet: A Lightweight Farmland Identification Network Integrating Local, Medium-Range, and Global Modeling

In high-resolution remote sensing imagery, farmland areas commonly exhibit blurred boundaries, discontinuous internal structures, and high similarity to non-farmland objects such as roads, bare soil, and low vegetation. Meanwhile, because pixel-level annotation is costly and training samples are difficult to obtain, only limited training data are often available in practical applications, making methods that rely on large-scale samples and complex model structures difficult to generalize effectively. To address these two issues, this paper proposes A3UNet, a multi-level attention-enhanced lightweight segmentation network for farmland identification from high-resolution remote sensing imagery. Based on a three-level encoder–decoder structure, the network introduces Point-Local Fusion Attention (PLFA), Medium-Range Attention (MRA), and Tri-Global Attention (TGA) into the skip connections, bottleneck layer, and intermediate decoder layer, respectively, thereby enhancing farmland feature representation from three levels: local boundaries, medium-range connected structures, and global semantic constraints. Few-sample experiments on two public datasets, GID and LoveDA, show that A3UNet achieves IoU values of 83.22% and 75.87%, respectively, with only 2.51 MB of parameters and 2.92 G FLOPs. Compared with the second-best methods on the corresponding datasets, the IoU is improved by 4.78 and 5.68 percentage points, respectively. These results indicate that the proposed method can achieve favorable identification accuracy and result stability while maintaining low model complexity, providing a lightweight solution with stronger practical application potential for farmland identification from high-resolution remote sensing imagery.