Efficient Meta-Learning Enabled Lightweight Multiscale Few-Shot Object Detection in Remote Sensing Images

TL;DR

This paper introduces a lightweight, meta-learning based multiscale few-shot object detection method for remote sensing images, improving accuracy and efficiency over existing models by leveraging a novel training framework and sample strategy.

Contribution

It proposes a novel meta-learning framework for lightweight one-stage detectors, specifically YOLOv7, tailored for multiscale few-shot object detection in remote sensing images.

Findings

Achieved superior detection accuracy on DIOR and NWPU VHR-10.v2 datasets.

Enhanced detection speed and model efficiency compared to traditional two-stage detectors.

Effectively utilized negative samples to improve meta-learning performance.

Abstract

Presently, the task of few-shot object detection (FSOD) in remote sensing images (RSIs) has become a focal point of attention. Numerous few-shot detectors, particularly those based on two-stage detectors, face challenges when dealing with the multiscale complexities inherent in RSIs. Moreover, these detectors present impractical characteristics in real-world applications, mainly due to their unwieldy model parameters when handling large amount of data. In contrast, we recognize the advantages of one-stage detectors, including high detection speed and a global receptive field. Consequently, we choose the YOLOv7 one-stage detector as a baseline and subject it to a novel meta-learning training framework. This transformation allows the detector to adeptly address FSOD tasks while capitalizing on its inherent advantage of lightweight. Additionally, we thoroughly investigate the samples generated by the meta-learning strategy and introduce a novel meta-sampling approach to retain samples produced by our designed meta-detection head. Coupled with our devised meta-cross loss, we deliberately utilize "negative samples" that are often overlooked to extract valuable knowledge from them. This approach serves to enhance detection accuracy and efficiently refine the overall meta-learning strategy. To validate the effectiveness of our proposed detector, we conducted performance comparisons with current state-of-the-art detectors using the DIOR and NWPU VHR-10.v2 datasets, yielding satisfactory results.