LALE：用于土地覆盖估计的轻量级Transformer架构
LALE: Lightweight-Transformer Architecture for Land-Cover Estimation
AI总结：
提出LALE架构，通过分辨率分支编码器（轻量级ConvMixer处理高分辨率局部特征，Transformer处理低分辨率全局上下文）和全MLP多尺度解码器，在遥感图像分割中实现高效性能与计算成本的平衡。
摘要：
遥感图像的语义分割需要模型在严格的计算预算下同时捕捉全局上下文和局部细节。先前的工作通常针对这些轴之一进行优化：注意力用于全局上下文，卷积用于局部细节，或紧凑性用于效率。虽然混合方法旨在同时捕捉两者，但它们需要架构更改和带有计算开销的编码器骨干，限制了效率和性能。我们提出了LALE（用于土地覆盖估计的轻量级Transformer架构），一种端到端的遥感图像分割架构，它通过分辨率分支编码器：轻量级ConvMixer阶段处理高分辨率局部特征，而Transformer阶段处理低分辨率全局上下文，将自注意力的二次成本限制在深层、下采样的特征图上。全MLP多尺度解码器，以及贯穿始终的RMSNorm和StarReLU，进一步减少了计算量和参数数量。在大型ARAS400k遥感分割基准上，LALE相对于CNN、Transformer和混合基线建立了强大的效率-性能权衡。我们最小的变体（仅1.6M参数）在F1分数上达到最佳基线（UPerNet）的2.6分以内，同时使用4.5倍更少的参数、7倍更少的存储、17倍更少的GMACs，并提供1.8倍更高的吞吐量。
英文摘要：
Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for global context, convolution for local detail, or compactness for efficiency. While hybrid approaches aim to capture both, they require architectural changes and encoder backbones with computational overhead, limiting efficiency and performance. We present LALE (Lightweight-transformer Architecture for Land-cover Estimation), an end-to-end remote sensing image segmentation architecture, that bifurcates its encoder by resolution: lightweight ConvMixer stages handle high-resolution local features, while transformer stages handle low-resolution global context, confining the quadratic cost of self-attention to deep, downsampled feature maps. An all-MLP multi-scale decoder, together with RMSNorm and StarReLU throughout, further reduces compute and parameter count. On the large-scale ARAS400k remote-sensing segmentation benchmark, LALE establishes a strong efficiency-performance trade-off against CNN, transformer, and hybrid baselines. Our smallest variant, (just 1.6M parameters), reaches within 2.6 F1 points of the best baseline (UPerNet) while using 4.5x fewer parameters, 7x less storage, 17x fewer GMACs, and delivering 1.8x higher throughput. The codebase for LALE is publicly available at https://github.com/caglarmert/LALE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
