Enhancing Cross Domain SAR Oil Spill Segmentation via Morphological Region Perturbation and Synthetic Label-to-SAR Generation
This work addresses a domain-specific challenge for remote sensing applications, particularly in oil spill monitoring along the Peruvian coast, and is incremental as it builds on existing methods with synthetic augmentation.
The paper tackles the problem of poor generalization of deep learning models for SAR oil spill segmentation across different regions, specifically from Mediterranean to Peruvian conditions, by proposing a two-stage synthetic augmentation framework that improves performance by up to +6 mIoU and boosts minority-class IoU significantly.
Deep learning models for SAR oil spill segmentation often fail to generalize across regions due to differences in sea-state, backscatter statistics, and slick morphology, a limitation that is particularly severe along the Peruvian coast where labeled Sentinel-1 data remain scarce. To address this problem, we propose \textbf{MORP--Synth}, a two-stage synthetic augmentation framework designed to improve transfer from Mediterranean to Peruvian conditions. Stage~A applies Morphological Region Perturbation, a curvature guided label space method that generates realistic geometric variations of oil and look-alike regions. Stage~B renders SAR-like textures from the edited masks using a conditional generative INADE model. We compile a Peruvian dataset of 2112 labeled 512$\times$512 patches from 40 Sentinel-1 scenes (2014--2024), harmonized with the Mediterranean CleanSeaNet benchmark, and evaluate seven segmentation architectures. Models pretrained on Mediterranean data degrade from 67.8\% to 51.8\% mIoU on the Peruvian domain; MORP--Synth improves performance up to +6 mIoU and boosts minority-class IoU (+10.8 oil, +14.6 look-alike).