Prompt guidance improves weak water mapping in multispectral images
Beyond Weak Labels: Prompt-Guided Local Refinement for Weakly Supervised Water Segmentation in High-Resolution Multispectral Imagery
Computer Vision and Pattern Recognition
Summary
Mapping water areas accurately in high-resolution satellite images is important but hard because detailed water labels are costly to make. The authors use rough water boundary data as a starting point, then improve these guesses by focusing on local areas that are often wrong. Their two-step method sharpens shorelines and catches small water details better. This makes water maps from satellite pictures more precise without needing expensive manual labels.
What this means in practice
- •For environmental monitoring teams: Produce more accurate water maps from satellite images using weak labels with improved local correction techniques enabled by this method.
- •For remote sensing software developers: Incorporate prompt-guided local refinement to enhance water segmentation models without needing extensive manual labeling.
Authors
Muhammad Farhan Humayun, Mohammad Imangholiloo, Afifah Shah, Tomi Westerlund, Jukka Heikkonen
Abstract
High-resolution water mapping supports environmental monitoring and related applications, but accurate pixel-level labels are difficult and costly to produce. Official hydrographic vectors provide scalable weak supervision, but they contain artifacts like boundary noise, temporal mismatch, and omissions of small water structures. We propose a two-stage framework for weakly supervised water segmentation in high resolution multispectral imagery. Stage 1 learns initial masks from rasterized vector pseudo-labels, and Stage 2 converts these masks into structured component-wise prompts for localized refinement. On a manually corrected validation set, refinement improves SegFormer-B0 from 0.9509 to 0.9535 IoU and U-Net from 0.9408 to 0.9486 IoU, with corresponding F1 gains from 0.9749 to 0.9762 and 0.9695 to 0.9736. It leads to sharper shorelines, reduced boundary spillover, and better thin-structure delineation. The results indicate that prompt-guided refinement can improve pseudo-label-based water segmentation by targeting local errors that are poorly captured by global training supervision.