LEAP:D -- A Novel Prompt-based Approach for Domain-Generalized Aerial Object Detection

TL;DR

This paper introduces LEAP:D, a prompt-based method utilizing learnable prompts and a streamlined training process to improve domain-generalized aerial object detection under varying drone imaging conditions.

Contribution

It proposes a novel vision-language approach with learnable prompts and a one-step training process, enhancing robustness and efficiency in aerial object detection across diverse environments.

Findings

Improved detection accuracy across different drone imaging conditions.

Reduced domain-specific knowledge interference with learnable prompts.

Streamlined training process with concurrent prompt and model updates.

Abstract

Drone-captured images present significant challenges in object detection due to varying shooting conditions, which can alter object appearance and shape. Factors such as drone altitude, angle, and weather cause these variations, influencing the performance of object detection algorithms. To tackle these challenges, we introduce an innovative vision-language approach using learnable prompts. This shift from conventional manual prompts aims to reduce domain-specific knowledge interference, ultimately improving object detection capabilities. Furthermore, we streamline the training process with a one-step approach, updating the learnable prompt concurrently with model training, enhancing efficiency without compromising performance. Our study contributes to domain-generalized object detection by leveraging learnable prompts and optimizing training processes. This enhances model robustness and adaptability across diverse environments, leading to more effective aerial object detection.