OilSAM2: Memory-Augmented SAM2 for Scalable SAR Oil Spill Detection

2026-03-10

AI Summary

This work addresses the performance instability in oil spill segmentation from synthetic aperture radar (SAR) imagery, which arises from highly variable appearances, heterogeneous scales, and the absence of temporal continuity. To tackle these challenges, the authors propose a memory-augmented segmentation framework tailored for unordered SAR sequences. Built upon the SAM2 architecture, the method integrates multi-level features encompassing texture, structure, and semantics, and introduces a hierarchical multi-scale memory bank coupled with a structure–semantic consistent memory update strategy. Additionally, selective memory refreshing and multi-scale feature alignment mechanisms are incorporated to effectively mitigate semantic drift and enhance cross-scene generalization. Evaluated on two public SAR oil spill datasets, the proposed approach achieves state-of-the-art performance and demonstrates robust, accurate segmentation even under noisy conditions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Segmenting oil spills from Synthetic Aperture Radar (SAR) imagery remains challenging due to severe appearance variability, scale heterogeneity, and the absence of temporal continuity in real world monitoring scenarios. While foundation models such as Segment Anything (SAM) enable prompt driven segmentation, existing SAM based approaches operate on single images and cannot effectively reuse information across scenes. Memory augmented variants (e.g., SAM2) further assume temporal coherence, making them prone to semantic drift when applied to unordered SAR image collections. We propose OilSAM2, a memory augmented segmentation framework tailored for unordered SAR oil spill monitoring. OilSAM2 introduces a hierarchical feature aware multi scale memory bank that explicitly models texture, structure, and semantic level representations, enabling robust cross image information reuse. To mitigate memory drift, we further propose a structure semantic consistent memory update strategy that selectively refreshes memory based on semantic discrepancy and structural variation.Experiments on two public SAR oil spill datasets demonstrate that OilSAM2 achieves state of the art segmentation performance, delivering stable and accurate results under noisy SAR monitoring scenarios. The source code is available at https://github.com/Chenshuaiyu1120/OILSAM2.

Problem

• SAR oil spill detection
• appearance variability
• scale heterogeneity
• temporal continuity
• semantic drift

Innovation

• memory-augmented segmentation
• hierarchical multi-scale memory bank
• structure-semantic consistent update
• unordered SAR imagery
• oil spill detection