PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
August 1, 2026˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesOpen Access

Meta-Prompting with Open-Source Language Models for Zero-Shot Scene Classification in Remote Sensing

View Full Paper
Ask AI
Bookmark
Share

Authors

APAntonis PromponasEBEirini BaltziVNValsamis Ntouskos

Discussion

Loading...

Member takes

Overview

Randomized trial investigates LLM-generated prompts for improving zero-shot scene classification in remote-sensing imagery, suggesting potential advancements in model efficiency.

Key Points

  • This research aims to evaluate the effectiveness of meta-prompting with open-source language models for zero-shot scene classification in remote-sensing imagery.
  • Investigated three open-source LLMs: Mixtral-8×7B, Qwen 2.5 7B, and LLaMA 3.1 8B.
  • Utilized five remote-sensing benchmark datasets for testing.
  • Compared LLM-generated prompts to generic and handcrafted domain-specific prompts using various vision-language models.
  • LLM-generated prompts were competitive with manually designed templates in zero-shot scene classification.
  • In some cases, LLM prompts improved classification accuracy, depending on dataset and visual backbone.
  • The potential of open-source LLMs was reinforced as scalable prompt generators for remote-sensing recognition.

Cite This Study

Promponas et al. (2026) studied this question.

synapsesocial.com/papers/6a6d984be258b358b3c6b754https://doi.org/10.5194/isprs-archives-xlix-b3-2026-233-2026
View Full Paper
Ask AI
Bookmark
Share