提出轻量高效的多光谱目标检测框架，提升可见与红外图像融合效果。
CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection
- 用重参数化块和跨模态注意力模块增强特征表达与融合效率。
- 在多个数据集上达到最高80.7% mAP50，兼顾精度与计算成本。
- 适合需要低延迟、高鲁棒性的多光谱感知系统部署。
RGB-T目标检测利用可见光与热成像的互补优势，在低光照、恶劣天气及复杂多尺度环境下实现鲁棒感知。现有方法仍存在跨模态交互不足、模态分布差异导致融合不稳定，以及基于注意力架构计算开销大的问题。为此，本文提出跨注意力融合梯度编程网络（CFGPNet），采用改进的GELAN骨干网络，结合RepViT风格的重参数化模块，在保持高效的同时强化特征表示。引入跨计算高效注意力（CrossCEA）模块，提升跨模态特征交互并减少可见光与热成像分支间的冗余信息传递。为生成紧凑且判别性强的融合表示，设计注意力选择与聚合融合（ASAF）网络，结合密集特征聚合与选择性注意力加权。此外，每个模型变体均集成可编程梯度辅助分支，改善梯度传播与优化质量。在五个公开多光谱基准（FLIR、M3FD、LLVIP、VEDAI、MFAD）上的实验表明，CFGPNet在多样场景、物体尺度和模态平衡下均表现出色，尤其在FLIR上达80.7% mAP50 / 45.0% mAP50:95，M3FD上达89.9% / 63.4%，LLVIP上达97.8% / 68.9%。在VEDAI与MFAD上分别取得83.3% / 56.9%和83.4% / 61.8%。结果验证了该框架在三类模型规模下均具备良好的精度-效率权衡能力。代码、数据与微调模型已开源。
原文摘要 · Abstract (English)
RGB--T object detection exploits the complementary strengths of visible and infrared imagery, supporting robust perception in low-light, adverse-weather, and complex multi-scale environments. However, existing methods still suffer from insufficient cross-modal interaction, unstable fusion from modality distribution gaps, and the high computational cost of heavy attention-based architectures. To address these issues, CFGPNet is proposed, a Cross-Attention-Based Fused Gradient Programmed Network framework for multispectral object detection. CFGPNet uses an improved GELAN backbone with RepViT-style re-parameterized blocks to strengthen feature representation while preserving computational efficiency. A Cross Computation Efficient Attention (CrossCEA) module is introduced to enhance cross-modal feature interaction and reduce redundant information transfer between visible and thermal branches. To generate compact and discriminative fused representations, an Attention Selection and Aggregation Fusion (ASAF) network combines dense feature aggregation with selective attention-based emphasis. Moreover, a programmable-gradient auxiliary branch is integrated into each CFGPNet variant to improve gradient delivery and optimization quality. Experiments on five public multispectral benchmarks, FLIR, M3FD, LLVIP, VEDAI, and MFAD, demonstrate that CFGPNet achieves strong and consistent performance across diverse scenes, object scales, and modality balances. In particular, the framework attains 80.7% mAP50 / 45.0% mAP50:95 on FLIR, 89.9% / 63.4% on M3FD, and 97.8% / 68.9% on LLVIP. It also reaches 83.3% / 56.9% on VEDAI and 83.4% / 61.8% on MFAD. These results show that CFGPNet is an effective, practical solution offering useful accuracy--efficiency trade-offs across three model scales. The code, data, and fine-tuned models are available at https://github.com/NimaHatami99/CFGPNet.
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。