Few-shot Oriented Object Detection with Memorable Contrastive Learning in Remote Sensing Images

TL;DR

This paper introduces a novel few-shot oriented object detection method for remote sensing images that employs oriented bounding boxes and contrastive learning to improve detection accuracy for arbitrarily oriented objects with limited data.

Contribution

It is the first to address few-shot oriented object detection in remote sensing images using oriented bounding boxes and a contrastive learning module with a dynamic memory bank.

Findings

Achieves state-of-the-art results on DOTA and HRSC2016 datasets.

Enhances feature discrimination for unseen classes.

Effectively detects arbitrarily oriented objects with limited training data.

Abstract

Few-shot object detection (FSOD) has garnered significant research attention in the field of remote sensing due to its ability to reduce the dependency on large amounts of annotated data. However, two challenges persist in this area: (1) axis-aligned proposals, which can result in misalignment for arbitrarily oriented objects, and (2) the scarcity of annotated data still limits the performance for unseen object categories. To address these issues, we propose a novel FSOD method for remote sensing images called Few-shot Oriented object detection with Memorable Contrastive learning (FOMC). Specifically, we employ oriented bounding boxes instead of traditional horizontal bounding boxes to learn a better feature representation for arbitrary-oriented aerial objects, leading to enhanced detection performance. To the best of our knowledge, we are the first to address oriented object detection in the few-shot setting for remote sensing images. To address the challenging issue of object misclassification, we introduce a supervised contrastive learning module with a dynamically updated memory bank. This module enables the use of large batches of negative samples and enhances the model's capability to learn discriminative features for unseen classes. We conduct comprehensive experiments on the DOTA and HRSC2016 datasets, and our model achieves state-of-the-art performance on the few-shot oriented object detection task. Code and pretrained models will be released.