Practical Techniques for Vision-Language Segmentation Model in Remote Sensing
Abstract. Traditional semantic segmentation models often struggle with poor generalizability in zero-shot scenarios such as recognizing attributes unseen in the training labels. On the other hands, language-vision models (VLMs) have shown promise in improving performance on zero-shot tasks by leveraging semantic information from textual inputs and fusing this information with visual features. However, existing VLM-based methods do not perform as effectively on remote sensing data due to the lack of such data in their training datasets. In this paper, we introduce a two-stage fine-tuning approach for a VLM-based segmentation model using a large remote sensing image-caption dataset, which we created using an existing image-caption model. Additionally, we propose a modified decoder and a visual prompt technique using a saliency map to enhance segmentation results. Through these methods, we achieve superior segmentation performance on remote sensing data, demonstrating the effectiveness of our approach.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
Practical Techniques for Vision-Language Segmentation Model in Remote Sensing ; volume:XLVIII-2-2024 ; year:2024 ; pages:203-210 ; extent:8
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; XLVIII-2-2024 (2024), 203-210 (gesamt 8)
- Creator
-
Lin, Yuting
Suzuki, Kumiko
Sogo, Shinichiro
- DOI
-
10.5194/isprs-archives-XLVIII-2-2024-203-2024
- URN
-
urn:nbn:de:101:1-2408051410527.834882234899
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
14.08.2025, 10:55 AM CEST
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Lin, Yuting
- Suzuki, Kumiko
- Sogo, Shinichiro
Other Objects (12)
Entropy based image segmentation and its application to remote sensing
GENERAL DEEP LEARNING SEGMENTATION PROCESS USED IN REMOTE SENSING IMAGES
Advanced single tree segmentation using high-resolution remote sensing data
Convolutional Neural Network for the Semantic Segmentation of Remote Sensing Images
RESEARCH ON METHOD OF INTERACTIVE SEGMENTATION BASED ON REMOTE SENSING IMAGES
Remote sensing image segmentation using feature based fusion on FCM clustering algorithm
An improved DeepLabv3+ lightweight network for remote-sensing image semantic segmentation
Remote sensing geology
Remote Sensing Deltas
Remote sensing geology
Aerosol remote sensing
Remote sensing geology
Entropy based image segmentation and its application to remote sensing
GENERAL DEEP LEARNING SEGMENTATION PROCESS USED IN REMOTE SENSING IMAGES
Advanced single tree segmentation using high-resolution remote sensing data
Convolutional Neural Network for the Semantic Segmentation of Remote Sensing Images
RESEARCH ON METHOD OF INTERACTIVE SEGMENTATION BASED ON REMOTE SENSING IMAGES
Remote sensing image segmentation using feature based fusion on FCM clustering algorithm
An improved DeepLabv3+ lightweight network for remote-sensing image semantic segmentation
Remote sensing geology
Remote Sensing Deltas
Remote sensing geology
Aerosol remote sensing
Remote sensing geology
Entropy based image segmentation and its application to remote sensing
GENERAL DEEP LEARNING SEGMENTATION PROCESS USED IN REMOTE SENSING IMAGES
Advanced single tree segmentation using high-resolution remote sensing data
Convolutional Neural Network for the Semantic Segmentation of Remote Sensing Images
RESEARCH ON METHOD OF INTERACTIVE SEGMENTATION BASED ON REMOTE SENSING IMAGES
Remote sensing image segmentation using feature based fusion on FCM clustering algorithm
An improved DeepLabv3+ lightweight network for remote-sensing image semantic segmentation
Remote sensing geology
Remote Sensing Deltas
Remote sensing geology
Aerosol remote sensing