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

TL;DR

This paper introduces a new underwater camouflaged instance segmentation dataset and a specialized segmentation network that significantly improves the accuracy of segmenting camouflaged marine organisms in underwater images.

Contribution

The paper presents the first underwater camouflaged instance segmentation dataset and a novel segmentation network with three modules tailored for underwater environments and camouflage challenges.

Findings

UCIS-SAM outperforms existing methods on UCIS4K and public benchmarks.

The proposed modules effectively enhance underwater feature learning and boundary detection.

The dataset provides a valuable resource for future underwater vision research.

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.