Utilizing deep learning for semantic segmentation of cropland from remote sensing imagery has become a crucial technique in land surveys. Cropland is highly heterogeneous and fragmented, and existing methods often suffer from inaccurate boundary segmentation. This paper introduces a UNet-like boundary-aware compensation model (BAFormer). Cropland boundaries typically exhibit rapid transformations in pixel values and texture features, often appearing as high-frequency features in remote sensing images. To enhance the recognition of these high-frequency features as represented by cropland boundaries, the proposed BAFormer integrates a Feature Adaptive Mixer (FAM) and develops a Depthwise Large Kernel Multi-Layer Perceptron model (DWLK-MLP) to enrich the global and local cropland boundaries features separately. Specifically, FAM enhances the boundary-aware method by adaptively acquiring high-frequency features through convolution and self-attention advantages, while DWLK-MLP further supplements boundary position information using a large receptive field. The efficacy of BAFormer has been evaluated on datasets including Vaihingen, Potsdam, LoveDA, and Mapcup. It demonstrates high performance, achieving mIoU scores of 84.5%, 87.3%, 53.5%, and 83.1% on these datasets, respectively. Notably, BAFormer-T (lightweight model) surpasses other lightweight models on the Vaihingen dataset with scores of 91.3% F1 and 84.1% mIoU.

Utilizing deep learning for semantic segmentation of cropland from remote sensing imagery has become a crucial technique in land surveys. Cropland illustrates diverse morphologies and degrees of fragmentation on the Earth’s surface, underscoring the importance of accurately perceiving the complex boundaries of cropland which are crucial for effective segmentation. This paper introduces a UNet-like boundary-aware compensation model BAFormer. Cropland boundaries typically exhibit rapid transformations in pixel values and texture features, often appearing as high-frequency features in remote-sensing images. To enhance the recognition of these high-frequency features as represented by cropland boundaries, the proposed BAFormer integrates a Feature Adaptive Mixer (FAM) and develops a Deep Wide Large Kernel Multi-Layer Perceptron (DWLK-MLP) to enrich the global and local cropland boundaries features separately. Specifically, FAM adaptively mixes high-frequency and low-frequency features through the advantages of convolution and self-attention; DWLK-MLP expands the convolutional receptive field by deeply decomposing large kernel convolutions. The efficacy of BAFormer has been evaluated on the Vaihingen, Potsdam, and LoveDA public datasets, as well as the Mapcup dataset. It has demonstrated advanced performance, achieving mIoU scores of 84.5%, 87.3%, 53.5%, and 83.1% on these datasets respectively. Notably, BAFormer-T, the lightweight iteration of the model, surpasses other lightweight models on the Vaihingen dataset with scores of 91.3% F1 and 84.1% mIoU. The source code is available at https://github.com/WangYouM1999/BAFormer.

Accurate farmland boundary mapping from high-resolution aerial imagery is vital for precision agriculture, yet existing methods struggle with complex geospatial boundaries and texture degradation in fragmented plots. To address irreversible detail loss under downsampling, difficulty in capturing both sharp boundaries and large-scale textures, and weak boundary supervision without extra annotations, we propose PaintingFormer, an enhanced UNet-based segmentation framework. It introduces three targeted innovations: an original feature retention module (OFRM) that injects raw RGB images into the deepest decoder layer to recover lost details; a dual attention–MLP design combining FeaAttention (full-resolution global attention with linear complexity) and TWLK-MLP (cascaded 3 × 3, 5 × 5, and 7 × 7 depthwise separable kernels within an MLP) to capture multi-scale spatial patterns; and a deep edge loss from the encoder’s bottleneck that enforces boundary constraints without manual edge labels. PaintingFormer surpasses mainstream methods, achieving 84.5% mIoU and 91.5% F1 on Vaihingen, 87.3% mIoU on Potsdam, 53.7% on LoveDA, and 84.2% on our private dataset. This work offers an effective solution for fine-grained farmland segmentation, improving boundary accuracy and texture preservation.