E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection
This work addresses a bottleneck in autonomous driving systems by simplifying multimodal fusion detection, though it appears incremental as it builds on existing methods with a novel training approach.
The paper tackles the problem of complex training processes in multimodal image fusion and object detection for autonomous driving by introducing E2E-MFD, an end-to-end algorithm that streamlines training and achieves performance gains, such as a 3.9% and 2.0% mAP50 increase on datasets M3FD and DroneVehicle compared to state-of-the-art methods.
Multimodal image fusion and object detection are crucial for autonomous driving. While current methods have advanced the fusion of texture details and semantic information, their complex training processes hinder broader applications. Addressing this challenge, we introduce E2E-MFD, a novel end-to-end algorithm for multimodal fusion detection. E2E-MFD streamlines the process, achieving high performance with a single training phase. It employs synchronous joint optimization across components to avoid suboptimal solutions tied to individual tasks. Furthermore, it implements a comprehensive optimization strategy in the gradient matrix for shared parameters, ensuring convergence to an optimal fusion detection configuration. Our extensive testing on multiple public datasets reveals E2E-MFD's superior capabilities, showcasing not only visually appealing image fusion but also impressive detection outcomes, such as a 3.9% and 2.0% mAP50 increase on horizontal object detection dataset M3FD and oriented object detection dataset DroneVehicle, respectively, compared to state-of-the-art approaches. The code is released at https://github.com/icey-zhang/E2E-MFD.