EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Soni, Sagar, Dudhane, Akshay, Debary, Hiyam, Fiaz, Mustansar, Munir, Muhammad Akhtar, Danish, Muhammad Sohail, Fraccaro, Paolo, Watson, Campbell D, Klein, Levente J, Khan, Fahad Shahbaz, Khan, Salman
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916675793715200
author Soni, Sagar
Dudhane, Akshay
Debary, Hiyam
Fiaz, Mustansar
Munir, Muhammad Akhtar
Danish, Muhammad Sohail
Fraccaro, Paolo
Watson, Campbell D
Klein, Levente J
Khan, Fahad Shahbaz
Khan, Salman
author_facet Soni, Sagar
Dudhane, Akshay
Debary, Hiyam
Fiaz, Mustansar
Munir, Muhammad Akhtar
Danish, Muhammad Sohail
Fraccaro, Paolo
Watson, Campbell D
Klein, Levente J
Khan, Fahad Shahbaz
Khan, Salman
contents Automated analysis of vast Earth observation data via interactive Vision-Language Models (VLMs) can unlock new opportunities for environmental monitoring, disaster response, and {resource management}. Existing generic VLMs do not perform well on Remote Sensing data, while the recent Geo-spatial VLMs remain restricted to a fixed resolution and few sensor modalities. In this paper, we introduce EarthDial, a conversational assistant specifically designed for Earth Observation (EO) data, transforming complex, multi-sensory Earth observations into interactive, natural language dialogues. EarthDial supports multi-spectral, multi-temporal, and multi-resolution imagery, enabling a wide range of remote sensing tasks, including classification, detection, captioning, question answering, visual reasoning, and visual grounding. To achieve this, we introduce an extensive instruction tuning dataset comprising over 11.11M instruction pairs covering RGB, Synthetic Aperture Radar (SAR), and multispectral modalities such as Near-Infrared (NIR) and infrared. Furthermore, EarthDial handles bi-temporal and multi-temporal sequence analysis for applications like change detection. Our extensive experimental results on 44 downstream datasets demonstrate that EarthDial outperforms existing generic and domain-specific models, achieving better generalization across various EO tasks. Our source codes and pre-trained models are at https://github.com/hiyamdebary/EarthDial.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15190
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
Soni, Sagar
Dudhane, Akshay
Debary, Hiyam
Fiaz, Mustansar
Munir, Muhammad Akhtar
Danish, Muhammad Sohail
Fraccaro, Paolo
Watson, Campbell D
Klein, Levente J
Khan, Fahad Shahbaz
Khan, Salman
Computer Vision and Pattern Recognition
Automated analysis of vast Earth observation data via interactive Vision-Language Models (VLMs) can unlock new opportunities for environmental monitoring, disaster response, and {resource management}. Existing generic VLMs do not perform well on Remote Sensing data, while the recent Geo-spatial VLMs remain restricted to a fixed resolution and few sensor modalities. In this paper, we introduce EarthDial, a conversational assistant specifically designed for Earth Observation (EO) data, transforming complex, multi-sensory Earth observations into interactive, natural language dialogues. EarthDial supports multi-spectral, multi-temporal, and multi-resolution imagery, enabling a wide range of remote sensing tasks, including classification, detection, captioning, question answering, visual reasoning, and visual grounding. To achieve this, we introduce an extensive instruction tuning dataset comprising over 11.11M instruction pairs covering RGB, Synthetic Aperture Radar (SAR), and multispectral modalities such as Near-Infrared (NIR) and infrared. Furthermore, EarthDial handles bi-temporal and multi-temporal sequence analysis for applications like change detection. Our extensive experimental results on 44 downstream datasets demonstrate that EarthDial outperforms existing generic and domain-specific models, achieving better generalization across various EO tasks. Our source codes and pre-trained models are at https://github.com/hiyamdebary/EarthDial.
title EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.15190