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

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

You might also read

Related Articles

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

Sort by

Same journal

Human-AI Interaction in Interventional Radiology: A Narrative Review of Current Applications, Challenges, and Future Directions.

Journal of imaging·2026

Same journal

Coronary Artery Anomalies and Anatomical Variants: Cross-Sectional Diagnostic Imaging and Clinical Background.

Journal of imaging·2026

Same journal

YoLeTooth: A Unified Framework for Joint Tooth Segmentation and Periapical Lesion Detection in Panoramic Radiographs.

Journal of imaging·2026

Same journal

Radiomics-Guided Multi-Sequence Learning for Pathological Complete Response Prediction from Breast MRI with Missing Auxiliary Sequences.

Journal of imaging·2026

Same journal

Cutaneous Thermography in Arthropathies: Quantitative Imaging, Machine Learning, and Clinical Translation.

Journal of imaging·2026

Same journal

Two-Stage Dynamic Synergistic Segmentation Method for Myocardial Pathology.

Journal of imaging·2026

Search research articles

Related Experiment Video

Updated: Apr 28, 2026

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

Vision and Language Reference for a Segment Anything Model for Few-Shot Segmentation.

Kosuke Sakurai¹, Ryotaro Shimizu², Masayuki Goto³

¹Graduate School of Creative Science and Engineering, Waseda University, Tokyo 169-8555, Japan.

Journal of Imaging

|April 27, 2026

Summary

This summary is machine-generated.

Vision and Language Reference Prompt into SAM (VLP-SAM) enhances few-shot segmentation by combining visual and text prompts. This multimodal approach improves accuracy and generalization for object segmentation tasks.

Keywords:

few-shot segmentation image segmentation multimodal learning segment anything model vision-language model

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

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: Apr 28, 2026

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

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

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 Science
Artificial Intelligence
Machine Learning

Background:

Few-shot segmentation models often struggle with accuracy due to reliance on visual cues alone.
Over-reliance on visual prompts leads to misidentification of visually similar objects from different categories.

Purpose of the Study:

To introduce a novel few-shot segmentation model, Vision and Language Reference Prompt into SAM (VLP-SAM).
To integrate both visual and semantic (textual) information into the Segment Anything Model (SAM) for improved segmentation.
To enhance segmentation accuracy and generalization capabilities by leveraging multimodal prompts.

Main Methods:

Developed VLP-SAM, a model integrating a vision-language model (VLM) with pixel-text matching into SAM's prompt encoder.
Incorporated task-specific structures like an attention mask to preserve SAM's segmentation knowledge while adding semantic context.
Utilized multimodal prompts (visual and textual) for few-shot segmentation.

Main Results:

VLP-SAM achieved superior few-shot segmentation performance with only 1.4 million learnable parameters.
Demonstrated significant improvements over previous methods on PASCAL-5^i and COCO-20^i datasets, with gains of 6.8% and 9.3% in mIoU, respectively.
Showcased strong generalization across unseen objects and cross-domain scenarios, attributed to textual semantic guidance.

Conclusions:

VLP-SAM offers an effective and scalable framework for few-shot segmentation using multimodal prompts.
Integrating textual semantic information significantly enhances segmentation robustness and accuracy.
The proposed model overcomes the limitations of purely visual prompt-based methods.