Multispectral-Fusion-Mechanism

Intro

Pytorch implementation of various cross-modality fusion mechanism in field of multispectral object detection.

Overview

Citation

If you are interested this repo for your research, welcome to cite our paper:

@article{qingyun2022cross,
  title={Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery},
  author={Qingyun, Fang and Zhaokui, Wang},
  journal={Pattern Recognition},
  pages={108786},
  year={2022},
  publisher={Elsevier}
}

Feature-based fusion

1. Cross-modality Interactive Attention (CIA)

Paper

Cross-modality interactive attention network for multispectral pedestrian detection. [Link]

Architecture

2. Gated Fusion Unit (GFU)

Paper

GFD-SSD: Gated Fusion Double SSD for Multispectral Pedestrian Detection. [Link]

Architecture

3. Multispectral Channel Feature Fusion (MCFF)

Paper

Attention fusion for one-stage multispectral pedestrian detection.[Link]

Architecture