Year: 2025
Type: preprint
Abstract: Oriented object detection for multi-spectral imagery faces significant challenges due to differences both within and between modalities. Although existing methods have improved detection accuracy through complex network architectures, their high computational complexity and memory consumption severely restrict their performance. Motivated by the success of large kernel convolutions in remote sensing, we propose MO R-CNN, a lightweight framework for multi-spectral oriented detection featuring heterogeneous feature extraction network (HFEN), single modality supervision (SMS), and condition-based multimodal label fusion (CMLF). HFEN leverages inter-modal differences to adaptively align, merge, and enhance multi-modal features. SMS constrains multi-scale features and enables the model to learn from multiple modalities. CMLF fuses multimodal labels based on specific rules, providing the model with a more robust and consistent supervisory signal. Experiments on the DroneVehicle, VEDAI and OGSOD datasets prove the superiority of our method. The source code is available at:https://github.com/Iwill-github/MORCNN.
Source: arXiv (Cornell University)
Authors: Wang, Leiyu, Jin, Biao, Huang, Feng, Chen, Liqiong, Wang, Zhengyong, He, Xiaohai, Chen, Honggang
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414745302