Few-shot Object Detection with Feature Attention Highlight Module in Remote Sensing Images

TL;DR

This paper introduces a novel few-shot object detection method tailored for remote sensing images, utilizing a feature attention highlight module to enhance detection accuracy with limited data, demonstrating promising experimental results.

Contribution

The paper proposes a lightweight feature attention highlight module integrated into a two-stage detector for effective few-shot object detection in remote sensing images, leveraging shared pre-trained features.

Findings

Effective detection of novel objects with few examples

The feature attention highlight module improves specificity of features

Demonstrated superior performance in remote sensing datasets

Abstract

In recent years, there are many applications of object detection in remote sensing field, which demands a great number of labeled data. However, in many cases, data is extremely rare. In this paper, we proposed a few-shot object detector which is designed for detecting novel objects based on only a few examples. Through fully leveraging labeled base classes, our model that is composed of a feature-extractor, a feature attention highlight module as well as a two-stage detection backend can quickly adapt to novel classes. The pre-trained feature extractor whose parameters are shared produces general features. While the feature attention highlight module is designed to be light-weighted and simple in order to fit the few-shot cases. Although it is simple, the information provided by it in a serial way is helpful to make the general features to be specific for few-shot objects. Then the object-specific features are delivered to the two-stage detection backend for the detection results. The experiments demonstrate the effectiveness of the proposed method for few-shot cases.