Cover Image

Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lian, Shijie, Zhang, Ziyi, Li, Hua, Li, Wenjie, Yang, Laurence Tianruo, Kwong, Sam, Cong, Runmin
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation
by: Li, Hua, et al.
Published: (2025)

Expose Camouflage in the Water: Underwater Camouflaged Instance Segmentation and Dataset
by: Wang, Chuhong, et al.
Published: (2025)

Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment
by: Lian, Shijie, et al.
Published: (2024)

UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken
by: Cong, Runmin, et al.
Published: (2025)

TUGS: Physics-based Compact Representation of Underwater Scenes by Tensorized Gaussian
by: Lian, Shijie, et al.
Published: (2025)

USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation
by: Hong, Lin, et al.
Published: (2025)

Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter
by: Chen, Zhiyang, et al.
Published: (2025)

WaterFlow: Explicit Physics-Prior Rectified Flow for Underwater Saliency Mask Generation
by: Li, Runting, et al.
Published: (2025)

USIS-PGM: Photometric Gaussian Mixtures for Underwater Salient Instance Segmentation
by: Hong, Lin, et al.
Published: (2026)

PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators
by: Cong, Runmin, et al.
Published: (2023)

From Sight to Insight: Unleashing Eye-Tracking in Weakly Supervised Video Salient Object Detection
by: Qin, Qi, et al.
Published: (2025)

RSONet: Region-guided Selective Optimization Network for RGB-T Salient Object Detection
by: Wan, Bin, et al.
Published: (2026)

SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection
by: Lin, Jia, et al.
Published: (2025)

Strike a Balance in Continual Panoptic Segmentation
by: Chen, Jinpeng, et al.
Published: (2024)

G2HFNet: GeoGran-Aware Hierarchical Feature Fusion Network for Salient Object Detection in Optical Remote Sensing Images
by: Wan, Bin, et al.
Published: (2026)

RDNet: Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network in Optical Remote Sensing Images
by: Wan, Bin, et al.
Published: (2026)

Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection
by: Cong, Runmin, et al.
Published: (2023)

UW-VOS: A Large-Scale Dataset for Underwater Video Object Segmentation
by: Zhao, Hongshen, et al.
Published: (2026)

MV-Adapter: Enhancing Underwater Instance Segmentation via Adaptive Channel Attention
by: Liu, Lianjun
Published: (2024)

KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection
by: Li, Xingyuan, et al.
Published: (2025)

BARIS: Boundary-Aware Refinement with Environmental Degradation Priors for Robust Underwater Instance Segmentation
by: Pan, Pin-Chi, et al.
Published: (2025)

Adapting Segment Anything Model for Unseen Object Instance Segmentation
by: Cao, Rui, et al.
Published: (2024)

Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Images
by: Ren, Mengyu, et al.
Published: (2025)

Tree-Mamba: A Tree-Aware Mamba for Underwater Monocular Depth Estimation
by: Zhuang, Peixian, et al.
Published: (2025)

Learning Dynamic Structural Specialization for Underwater Salient Object Detection
by: Hong, Lin, et al.
Published: (2026)

Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios
by: Guo, Guangqian, et al.
Published: (2026)

Exploring the Underwater World Segmentation without Extra Training
by: Li, Bingyu, et al.
Published: (2025)

SPLF-SAM: Self-Prompting Segment Anything Model for Light Field Salient Object Detection
by: Xu, Qiyao, et al.
Published: (2025)

Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future
by: Chen, Long, et al.
Published: (2024)

Adapting Segment Anything Model to Multi-modal Salient Object Detection with Semantic Feature Fusion Guidance
by: Wang, Kunpeng, et al.
Published: (2024)

Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection
by: Gao, Shixuan, et al.
Published: (2024)

HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detection
by: Hou, Ruichao, et al.
Published: (2025)

Underwater Variable Zoom: Depth-Guided Perception Network for Underwater Image Enhancement
by: Huang, Zhixiong, et al.
Published: (2024)

Matching Anything by Segmenting Anything
by: Li, Siyuan, et al.
Published: (2024)

PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model
by: Deng, Zhongchen, et al.
Published: (2024)

UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching
by: Lv, Qingxuan, et al.
Published: (2024)

The Common Objects Underwater (COU) Dataset for Robust Underwater Object Detection
by: Mukherjee, Rishi, et al.
Published: (2025)

SPDA-SAM: A Self-prompted Depth-Aware Segment Anything Model for Instance Segmentation
by: Shang, Yihan, et al.
Published: (2026)

ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation
by: Bi, Hanbo, et al.
Published: (2025)

Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection
by: Li, Feiran, et al.
Published: (2024)