Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shuaiyu Chen, Ming Yin, Peng Ren, Chunbo Luo, Zeyu Fu

TL;DR

The proposed 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 and to mitigate memory drift.

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.

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

TL;DR

The proposed 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 and to mitigate memory drift.

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.
Paper Structure (12 sections, 11 equations, 2 figures, 3 tables)

This paper contains 12 sections, 11 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Problem Formulation
  4. Hierarchical Feature-Aware Memory Bank
  5. Scale-Adaptive Memory Fusion
  6. Structure-Semantic Consistent Memory Update
  7. Experiments
  8. Datasets
  9. Implementation Details
  10. Comparison with State-of-the-Art
  11. Ablation Study
  12. Conclusion

Figures (2)

  • Figure 1: Overview of the proposed OilSAM2 framework. Given an input SAR image and user prompt, hierarchical features are extracted and organized into texture-, structure-, and semantic-level representations. Each level interacts with a corresponding memory group via scale-wise attention. The retrieved features are adaptively fused and decoded to produce the segmentation mask, while a structure–semantic consistent update strategy regulates memory refreshing for robust reuse across unordered SAR images.
  • Figure 2: Qualitative results of the ablation study(On SOS Dataset).