Papers › UWSAM: Segment Anything Model Guided Underwater Instance Segmentation and A...

UWSAM: Segment Anything Model Guided Underwater Instance Segmentation and A Large-scale Benchmark Dataset

21 May 2025arXiv:2505.15581archive 2025-07-28

Hua Li, Shijie Lian, Zhiyuan Li, Runmin Cong, Sam Kwong

With recent breakthroughs in large-scale modeling, the Segment Anything Model (SAM) has demonstrated significant potential in a variety of visual applications. However, due to the lack of underwater domain expertise, SAM and its variants face performance limitations in end-to-end underwater instance segmentation tasks, while their higher computational requirements further hinder their application in underwater scenarios. To address this challenge, we propose a large-scale underwater instance segmentation dataset, UIIS10K, which includes 10,048 images with pixel-level annotations for 10 categories. Then, we introduce UWSAM, an efficient model designed for automatic and accurate segmentation of underwater instances. UWSAM efficiently distills knowledge from the SAM ViT-Huge image encoder into the smaller ViT-Small image encoder via the Mask GAT-based Underwater Knowledge Distillation (MG-UKD) method for effective visual representation learning. Furthermore, we design an End-to-end Underwater Prompt Generator (EUPG) for UWSAM, which automatically generates underwater prompts instead of explicitly providing foreground points or boxes as prompts, thus enabling the network to locate underwater instances accurately for efficient segmentation. Comprehensive experimental results show that our model is effective, achieving significant performance improvements over state-of-the-art methods on multiple underwater instance datasets. Datasets and codes are available at https://github.com/LiamLian0727/UIIS10K.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

liamlian0727/uiis10k officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationKnowledge DistillationRepresentation LearningSegmentationSemantic Segmentation

Datasets

Introduced by this paper, per the archive.

UIIS10K

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge DistillationSAM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections