Semi-Supervised Object Detection in Remote Sensing Images Based on Active Learning

Abstract

The emergence of Semi-Supervised Object Detection (SSOD) techniques has led to notable improvements in object detection capabilities by leveraging a restricted quantity of labeled data and a copious amount of unlabeled data. However, there are two challenging issues that need to be addressed in remote sensing images. Firstly, the complex background and large variation in target scales in remote sensing images can result in poor quality of pseudo-labels. Secondly, the long-tailed distribution problem, where some categories have a large number of instances while others have very few, is also common in remote sensing images. In this paper, we address SSOD in remote sensing images characterized by a long-tailed distribution. We propose an active learning strategy for selecting labeled data in the process of semi-supervised learning. The model training is decoupled into the training of backbone and detector. This idea contributes to favorable improvement in the regression branch and our method can achieve significant results on DOTA-v1.0 dataset.