Interactive Masked Image Modeling for Multimodal Object Detection in Remote Sensing

TL;DR

This paper introduces an interactive masked image modeling approach that leverages self-supervised learning to improve multimodal object detection in remote sensing imagery, especially for small and barely visible objects.

Contribution

The paper proposes a novel interactive MIM method that enhances token interactions, addressing limitations of conventional MIM for fine-grained remote sensing object detection.

Findings

Improved detection accuracy on remote sensing datasets.

Effective use of self-supervised pre-training with unlabeled data.

Demonstrated superiority over traditional MIM methods.

Abstract

Object detection in remote sensing imagery plays a vital role in various Earth observation applications. However, unlike object detection in natural scene images, this task is particularly challenging due to the abundance of small, often barely visible objects across diverse terrains. To address these challenges, multimodal learning can be used to integrate features from different data modalities, thereby improving detection accuracy. Nonetheless, the performance of multimodal learning is often constrained by the limited size of labeled datasets. In this paper, we propose to use Masked Image Modeling (MIM) as a pre-training technique, leveraging self-supervised learning on unlabeled data to enhance detection performance. However, conventional MIM such as MAE which uses masked tokens without any contextual information, struggles to capture the fine-grained details due to a lack of interactions with other parts of image. To address this, we propose a new interactive MIM method that can establish interactions between different tokens, which is particularly beneficial for object detection in remote sensing. The extensive ablation studies and evluation demonstrate the effectiveness of our approach.