RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multiscale Receptive Fields and Foreground Focus Mechanism
This work addresses accuracy and efficiency issues in remote sensing object detection, offering a lightweight solution for applications like aerial imagery analysis, though it appears incremental as it builds on existing detection frameworks.
The paper tackled challenges in remote sensing object detection, such as small object sizes and imbalanced foreground-background distribution, by proposing RFWNet, which achieved 95.3% mAP on DOTA V1.0 and 73.2% mAP on NWPU VHR-10 with 6.0 M parameters and 52 FPS inference speed.
Challenges in remote sensing object detection(RSOD), such as high interclass similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images, significantly hinder detection accuracy. Moreover, the tradeoff between model accuracy and computational complexity poses additional constraints on the application of RSOD algorithms. To address these issues, this study proposes an efficient and lightweight RSOD algorithm integrating multiscale receptive fields and foreground focus mechanism, named robust foreground weighted network(RFWNet). Specifically, we proposed a lightweight backbone network receptive field adaptive selection network (RFASNet), leveraging the rich context information of remote sensing images to enhance class separability. Additionally, we developed a foreground-background separation module(FBSM)consisting of a background redundant information filtering module (BRIFM) and a foreground information enhancement module (FIEM) to emphasize critical regions within images while filtering redundant background information. Finally, we designed a loss function, the weighted CIoU-Wasserstein loss (LWCW),which weights the IoU-based loss by using the normalized Wasserstein distance to mitigate model sensitivity to small object position deviations. The comprehensive experimental results demonstrate that RFWNet achieved 95.3% and 73.2% mean average precision (mAP) with 6.0 M parameters on the DOTA V1.0 and NWPU VHR-10 datasets, respectively, with an inference speed of 52 FPS.