Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Global burden of maternal disorders, 1990-2021: insights from the Global Burden of Disease Study 2021 and challenges for achieving 2030 Sustainable Development Goals.

Journal of global health·2026

Same author

Reducing selection bias risk to enhance RCT validity: sandwich mixed randomization outperforms permuted block design.

BMC medical research methodology·2026

Same author

Dual object graph and bisimulation metric for object-goal navigation in unfamiliar environment.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Lysine methyltransferase Sll0171 modulates motility through PilA1 methylation in Synechocystis sp. PCC 6803.

Plant physiology·2026

Same author

Estimating the global macroeconomic impact of colorectal cancer: evidence from Global Burden of Disease 2021 and Value of a Statistical Life Year framework.

International journal of surgery (London, England)·2026

Same author

Achieving impact-buffered compressible batteries through 3D printing-assisted design of negative Poisson's ratio structural electrodes.

Fundamental research·2026

Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 14, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

SAMSnake: A generic contour-based instance segmentation network assisted by Efficient Segment Anything Model.

Yejun Wu¹, Jiao Zhan², Chi Guo³

¹School of Computer Science, Wuhan University, Wuhan, 430072, Hubei, China.

Neural Networks : the Official Journal of the International Neural Network Society

|May 12, 2025

Summary

This summary is machine-generated.

SAMSNAKE, a new contour-based instance segmentation network, enhances flexibility and precision. It achieves state-of-the-art results on multiple benchmarks using novel contour initialization and optimization modules.

Keywords:

Amodal segmentation Contour-based Deep neural network EfficientSAM Instance segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: May 14, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Computer Vision
Deep Learning
Image Segmentation

Background:

Contour-based instance segmentation is crucial for precise object boundary detection.
Existing methods face limitations in flexibility and initialization accuracy.

Purpose of the Study:

Introduce SAMSnake, a novel contour-based instance segmentation network.
Enhance the flexibility of contour segmentation for downstream tasks.
Improve the accuracy of contour initialization and refinement.

Main Methods:

Decoupled detector from traditional contour segmentation framework.
Developed EfficientSAM-based Contour Initialization (ECI) module for accurate initial contours.
Integrated Dynamic Matching Loss (DML) and normalization offsets in the Normalization Contour Optimization (NCO) module.
Utilized heatmap and boundary map supervision for training stability.

Main Results:

Achieved state-of-the-art performance across multiple benchmark datasets.
Reported mAP scores: 36.4% (Cityscapes), 61.4% (SBD), 38.8% (COCO), 36.7% (KINS), 46.0% (COCOA).
Demonstrated high precision in contour deformation refinement.

Conclusions:

SAMSNAKE offers a flexible and high-performance solution for contour-based instance segmentation.
The proposed ECI and NCO modules significantly improve contour initialization and refinement.
The method sets a new standard in instance segmentation accuracy and efficiency.