轻量级多光谱遥感目标检测模型，提升精度同时降低计算开销。
MO R-CNN: Multispectral Oriented R-CNN for Object Detection in Remote Sensing Image
- 通过异质特征网络自适应融合多模态特征
- 在三个数据集上实现更高检测精度且更轻量化
- 适合资源受限场景下的遥感图像目标检测
多光谱遥感图像中的定向目标检测面临模态内与模态间差异的挑战。现有方法虽通过复杂网络提升精度，但计算量与内存消耗过大。受大核卷积在遥感中成功应用启发，本文提出MO R-CNN，一种轻量级多光谱定向检测框架，包含异质特征提取网络（HFEN）、单模态监督（SMS）和基于条件的多模态标签融合（CMLF）。HFEN利用模态间差异自适应对齐、融合与增强多模态特征；SMS约束多尺度特征，使模型能从多模态学习；CMLF根据特定规则融合多模态标签，提供更鲁棒一致的监督信号。在DroneVehicle、VEDAI和OGSOD数据集上的实验验证了该方法的优越性。代码已开源：https://github.com/Iwill-github/MORCNN。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。