paper-with-me

Papers

E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection

2024-03-14 · Jiaqing Zhang, Mingxiang Cao, Weiying Xie, Jie Lei, Daixun Li, Wenbo Huang, Yunsong Li, Xue Yang

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.

📄 PDF Abstract BibTeX arXiv:2403.09323

Code (1)

icey-zhang/E2E-MFD 공식 구현 pytorch

Tasks

Autonomous DrivingObjectobject-detectionObject DetectionOriented Object Detection

Similar Papers 제목 키워드 기반

FGU3R: Fine-Grained Fusion via Unified 3D Representation for Multimodal 3D Object Detection

2025-01-08 · Guoxin Zhang, Ziying Song, Lin Liu, Zhonghong Ou

Multimodal 3D object detection has garnered considerable interest in autonomous driving. However, multimodal detectors suffer from dimension mismatches that derive from fusing 3D points with 2D pixels coarsely, which lea…

3D Object DetectionAutonomous Drivingmultimodal interactionobject-detection+1

Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph

2018-07-01 · ACL 2018 7 · AmirAli Bagher Zadeh, Paul Pu Liang, Soujanya Poria, Erik Cambria 외

Analyzing human multimodal language is an emerging area of research in NLP. Intrinsically this language is multimodal (heterogeneous), sequential and asynchronous; it consists of the language (words), visual (expressions…

Emotion RecognitionLanguage ModelingLanguage ModellingMultimodal Sentiment Analysis+2

SODFormer: Streaming Object Detection with Transformer Using Events and Frames

2023-08-08 · Dianze Li, Jianing Li, Yonghong Tian

DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to…

object-detectionObject Detection

ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing

2025-07-07 · Zhenghui Zhao, Chen Wu, Xiangyong Cao, Di Wang 외 arxiv

Spatiotemporal image generation is a highly meaningful task, which can generate future scenes conditioned on given observations. However, existing change generation methods can only handle event-driven changes (e.g., new…

Change DetectionImage Generation

Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations

2024-07-06 · Dingkang Yang, Mingcheng Li, Linhao Qu, Kun Yang 외

Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural l…