Enhanced LULC Segmentation via Lightweight Model Refinements on ALOS-2 SAR Data

TL;DR

This paper presents lightweight model refinements for improved land-cover segmentation and water detection using ALOS-2 SAR data, addressing common dense-prediction issues without added complexity.

Contribution

It introduces three novel lightweight refinements that enhance boundary accuracy, thin structure detection, and class balance in SAR-based LULC segmentation.

Findings

Improved segmentation accuracy on Japan-wide ALOS-2 dataset.

Enhanced detection of under-represented land classes.

Better water detection performance across metrics.

Abstract

This work focuses on national-scale land-use/land-cover (LULC) semantic segmentation using ALOS-2 single-polarization (HH) SAR data over Japan, together with a companion binary water detection task. Building on SAR-W-MixMAE self-supervised pretraining [1], we address common SAR dense-prediction failure modes, boundary over-smoothing, missed thin/slender structures, and rare-class degradation under long-tailed labels, without increasing pipeline complexity. We introduce three lightweight refinements: (i) injecting high-resolution features into multi-scale decoding, (ii) a progressive refine-up head that alternates convolutional refinement and stepwise upsampling, and (iii) an $\alpha$-scale factor that tempers class reweighting within a focal+dice objective. The resulting model yields consistent improvements on the Japan-wide ALOS-2 LULC benchmark, particularly for under-represented classes, and improves water detection across standard evaluation metrics.