Platform motion errors degrade SAR image quality in terms of severe defocusing and azimuth blurring. We propose a Range-aware Autofocus Network (RAFnet) by embedding a novel range-aware attention module into a progressive autofocus framework. The module exploits 1-D azimuth pooling to compress spatial features and extract high-SNR scattering components from the range dimension. Such features are further enriched via a light cross-channel interaction. To facilitate coarse-to-fine hierarchical learning, we develop a progressive multi-scale entropy loss which jointly optimizes the entire network. Experimental results on real SAR data show that the proposed approach captures high-level phase fluctuations accurately and effectively suppresses raw phase deviations and sidelobes. Quantitative results show that combining the attention module with multi-scale loss achieved a global spatial entropy of 9.8567 and contrast of 5.0091 in focused images. By extracting more accurate focus-oriented feature representations, we provide an effective solution for high-quality SAR auto-focusing.
Accurate delineation of landslides in RGB optical remote sensing imagery supports rapid disaster mapping and post-event assessment. This remains difficult because landslides are often small and irregular, resemble bare soil or disturbed vegetation, and acquire blurred boundaries when images are resized. We developed AS-UNet, a lightweight U-Net variant with three targeted modifications. The Asymmetric Strip Attention Module uses horizontal and vertical depthwise strip convolutions with parallel channel-spatial reweighting to capture anisotropic landslide morphology. The Channel-Spatial Joint Gate uses decoder semantics to filter selected skip connections while retaining channel-specific spatial responses. The Poly-Harmonized Gradient Dice Loss (PGD Loss) combines pixel-wise, region-overlap, gradient-density, and probability-regularization terms for imbalanced segmentation. At 128 × 128 input resolution, AS-UNet achieved a best-validation IoU of 80.46 ± 0.03% and an independent-test IoU of 77.82 ± 0.32% across three random seeds. AS-UNet contains 8.634 M parameters and processed 380.79 frames per second on the reported hardware. These results indicate a favorable balance between segmentation accuracy and computational efficiency for RGB optical landslide mapping.