DEPFusion: Dual-Domain Enhancement and Priority-Guided Mamba Fusion for UAV Multispectral Object Detection
On the map: State-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Abstract (arXiv)
Multispectral object detection is an important application for unmanned aerial vehicles (UAVs). However, it faces several challenges. First, low-light RGB images weaken the multispectral fusion due to details loss. Second, the interference information is introduced to local target modeling during multispectral fusion. Third, computational cost poses deployment challenge on UAV platforms, such as transformer-based methods with quadratic complexity. To address these issues, a framework named DEPFusion consisting of two designed modules, Dual-Domain Enhancement (DDE) and Priority-Guided Mamba Fusion (PGMF) , is proposed for UAV multispectral object detection. Firstly, considering the adoption of low-frequency component for global brightness enhancement and frequency spectra features for texture-details recovery, DDE module is designed with Cross-Scale Wavelet Mamba (CSWM) block and Fourier Details Recovery (FDR) block. Secondly, considering guiding the scanning of Mamba from high priority score tokens, which contain local target feature, a novel Priority-Guided Serialization is proposed with theoretical proof. Based on it, PGMF module is designed for multispectral feature fusion, which enhance local modeling and reduce interference information. Experiments on DroneVehicle and VEDAI datasets demonstrate that DEPFusion achieves good performance with state-of-the-art methods.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 39 of its 76 references that are in the map. First posted on arXiv 9 Sep 2025.
Builds on
39 of 76 references.
Closest ancestors · 1
Same direction, newest first
Other references · 38
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2015Fast R-CNNcited by 2,933
- 2018YOLOv3: An Incremental Improvementcited by 2,659
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
- 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
- 2024VMamba: Visual State Space Modelcited by 969
- 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 317
- 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 287
- 2021Oriented R-CNN for Object Detectioncited by 231
- 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 231
- 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
- 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 194
26 more
- 2020Align Deep Features for Oriented Object Detectioncited by 187
- 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
- 2020Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learningcited by 152
- 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 127
- 2022MMRotate: A Rotated Object Detection Benchmark using PyTorchcited by 115
- 2022Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baselinecited by 91
- 2020Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problemscited by 83
- 2023Low-Light Image Enhancement via Structure Modeling and Guidancecited by 79
- 2022The KFIoU Loss for Rotated Object Detectioncited by 73
- 2023C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detectioncited by 58
- 2023Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusioncited by 54
- 2024Poly Kernel Inception Network for Remote Sensing Detectioncited by 52
- 2022Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detectioncited by 50
- 2024Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancementcited by 48
- 2022SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagerycited by 47
- 2022Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detectioncited by 46
- 2021Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagerycited by 45
- 2024SpectralMamba: Efficient Mamba for Hyperspectral Image Classificationcited by 36
- 2025DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusioncited by 34
- 2022Weakly Aligned Feature Fusion for Multimodal Object Detectioncited by 26
- 2024Task-driven Image Fusion with Learnable Fusion Losscited by 25
- 2022Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modelingcited by 23
- 2024Low-Light Image Enhancement via Generative Perceptual Priorscited by 21
- 2023TFDet: Target-Aware Fusion for RGB-T Pedestrian Detectioncited by 18
- 2024Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detectioncited by 16
- 2025Generalization-Enhanced Few-Shot Object Detection in Remote Sensingcited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV Detection
- 2025WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection
- 2025MambaRefine-YOLO: A Dual-Modality Small Object Detector for UAV Imagery
- 2026DLRMamba: Distilling Low-Rank Mamba for Edge Multispectral Fusion Object Detection
- 2024RemoteDet-Mamba: A Hybrid Mamba-CNN Network for Multi-modal Object Detection in Remote Sensing Images
- 2026YOLO12-MambaScan: An Efficient Object Detector with High-Frequency Enhancement and State-Space Modeling
- 2024MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking
- 2025D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal