mlsanityData to 7 Oct 2026

Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks

arXiv 2009.12664 ↗First posted 26 Sep 2020cs.CVcited by 85

Not on the map. Why?

Abstract (arXiv)

Multispectral images (e.g. visible and infrared) may be particularly useful when detecting objects with the same model in different environments (e.g. day/night outdoor scenes). To effectively use the different spectra, the main technical problem resides in the information fusion process. In this paper, we propose a new halfway feature fusion method for neural networks that leverages the complementary/consistency balance existing in multispectral features by adding to the network architecture, a particular module that cyclically fuses and refines each spectral feature. We evaluate the effectiveness of our fusion method on two challenging multispectral datasets for object detection. Our results show that implementing our Cyclic Fuse-and-Refine module in any network improves the performance on both datasets compared to other state-of-the-art multispectral object detection methods.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 10; 2024: 21; 2025: 26; 2026: 21.

85 papers.

Sort:

By area:

  1. 2021Cross-Modality Fusion Transformer for Multispectral Object Detectioncited by 86
  2. 2023ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detectioncited by 76
  3. 2021Multimodal Object Detection via Probabilistic Ensemblingcited by 67
  4. 2024Fusion-Mamba for Cross-modality Object Detectioncited by 67
  5. 2023Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusioncited by 54
  6. 2025Infrared and Visible Image Fusion: From Data Compatibility to Task Adaptioncited by 45
  7. 2024DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusioncited by 28
  8. 2022Weakly Aligned Feature Fusion for Multimodal Object Detectioncited by 26
  9. 2022Emergent Visual Sensors for Autonomous Vehiclescited by 18
  10. 2023TFDet: Target-Aware Fusion for RGB-T Pedestrian Detectioncited by 18
  11. 2024Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detectioncited by 16
  12. 2024UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuningcited by 16
38 more
  1. 2025DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understandingcited by 16
  2. 2023RGB-X Object Detection via Scene-Specific Fusion Modulescited by 15
  3. 2023MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimizationcited by 14
  4. 2025WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detectioncited by 14
  5. 2021BAANet: Learning Bi-directional Adaptive Attention Gates for Multispectral Pedestrian Detectioncited by 13
  6. 2024Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detectioncited by 13
  7. 2025ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translationcited by 13
  8. 2024When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Datasetcited by 10
  9. 2024D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detectioncited by 9
  10. 2024Rethinking Early-Fusion Strategies for Improved Multispectral Object Detectioncited by 9
  11. 2025R-LiViT: A LiDAR-Visual-Thermal Dataset Enabling Vulnerable Road User Focused Roadside Perceptioncited by 9
  12. 2023HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Informationcited by 8
  13. 2024Pedestrian Detection in Low-Light Conditions: A Comprehensive Surveycited by 8
  14. 2024CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weathercited by 8
  15. 2025M-SpecGene: Generalized Foundation Model for RGBT Multispectral Visioncited by 8
  16. 2024Visual Modality Prompt for Adapting Vision-Language Object Detectorscited by 7
  17. 2023Online Self-Supervised Thermal Water Segmentation for Aerial Vehiclescited by 6
  18. 2024MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detectioncited by 6
  19. 2025Multispectral State-Space Feature Fusion: Bridging Shared and Cross-Parametric Interactions for Object Detectioncited by 6
  20. 2024MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detectioncited by 5
  21. 2024Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Surveycited by 5
  22. 2024DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detectioncited by 5
  23. 2025Learning A Robust RGB-Thermal Detector for Extreme Modality Imbalancecited by 5
  24. 2025C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detectioncited by 5
  25. 2022Robust Environment Perception for Automated Driving: A Unified Learning Pipeline for Visual-Infrared Object Detectioncited by 4
  26. 2024Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledgecited by 4
  27. 2024SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detectioncited by 4
  28. 2024Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarkscited by 4
  29. 2025SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systemscited by 4
  30. 2026SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detectioncited by 4
  31. 2023Cascaded information enhancement and cross-modal attention feature fusion for multispectral pedestrian detectioncited by 3
  32. 2024MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detectioncited by 3
  33. 2024DiffX: Guide Your Layout to Cross-Modal Generative Modelingcited by 3
  34. 2025YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Frameworkcited by 3
  35. 2025RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarioscited by 3
  36. 2026TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translationcited by 3
  37. 2021Partially fake it till you make it: mixing real and fake thermal images for improved object detectioncited by 2
  38. 2023Multimodal Object Detection in Remote Sensingcited by 1

50 most cited of 85 All 85 (JSON)