Expose Camouflage in the Water: Underwater Camouflaged Instance Segmentation and Dataset

2025-10-20

AI Summary

To address low segmentation accuracy in underwater camouflaged instance segmentation (UCIS) caused by color distortion, low contrast, and blur, this work formally defines the UCIS task for the first time and introduces UCIS4K—the first large-scale underwater camouflaged dataset. We propose UCIS-SAM, a novel adaptation of the Segment Anything Model (SAM), incorporating three key modules: a channel-balancing optimization module to rectify color bias, a frequency-domain true fusion module to preserve structural details under degradation, and a multi-scale frequency-domain aggregation module to enhance feature discrimination and boundary delineation of concealed marine organisms. Extensive experiments demonstrate that UCIS-SAM achieves significant performance gains over state-of-the-art methods on both the UCIS4K benchmark and cross-domain underwater datasets. This work establishes a foundational data–model framework and a new paradigm for understanding underwater visual camouflage.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

With the development of underwater exploration and marine protection, underwater vision tasks are widespread. Due to the degraded underwater environment, characterized by color distortion, low contrast, and blurring, camouflaged instance segmentation (CIS) faces greater challenges in accurately segmenting objects that blend closely with their surroundings. Traditional camouflaged instance segmentation methods, trained on terrestrial-dominated datasets with limited underwater samples, may exhibit inadequate performance in underwater scenes. To address these issues, we introduce the first underwater camouflaged instance segmentation (UCIS) dataset, abbreviated as UCIS4K, which comprises 3,953 images of camouflaged marine organisms with instance-level annotations. In addition, we propose an Underwater Camouflaged Instance Segmentation network based on Segment Anything Model (UCIS-SAM). Our UCIS-SAM includes three key modules. First, the Channel Balance Optimization Module (CBOM) enhances channel characteristics to improve underwater feature learning, effectively addressing the model's limited understanding of underwater environments. Second, the Frequency Domain True Integration Module (FDTIM) is proposed to emphasize intrinsic object features and reduce interference from camouflage patterns, enhancing the segmentation performance of camouflaged objects blending with their surroundings. Finally, the Multi-scale Feature Frequency Aggregation Module (MFFAM) is designed to strengthen the boundaries of low-contrast camouflaged instances across multiple frequency bands, improving the model's ability to achieve more precise segmentation of camouflaged objects. Extensive experiments on the proposed UCIS4K and public benchmarks show that our UCIS-SAM outperforms state-of-the-art approaches.

Problem

• Segmenting camouflaged marine organisms in degraded underwater environments
• Addressing limited underwater samples in traditional camouflaged instance segmentation
• Improving segmentation accuracy for objects blending with underwater surroundings

Innovation

• Channel Balance Optimization Module enhances underwater feature learning
• Frequency Domain True Integration Module reduces camouflage pattern interference
• Multi-scale Feature Frequency Aggregation Module strengthens object boundaries