Image-Fusion-Transformer

Platform

Python 3.7
Pytorch >=1.0

Training Dataset

MS-COCO 2014 (T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, and C. L. Zitnick. Microsoft coco: Common objects in context. In ECCV, 2014. 3-5.) is utilized to train our auto-encoder network.

KAIST (S. Hwang, J. Park, N. Kim, Y. Choi, I. So Kweon, Multispectral pedestrian detection: Benchmark dataset and baseline, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1037–1045.) is utilized to train the RFN modules.

The testing datasets are included in "analysis_MatLab".

Training Command:

python train_vit_fusionnet.py

Testing Command:

python test_21pairs_vit.py

The Fusion results are included in "analysis_MatLab".

If you have any question about this code, feel free to reach me([email protected]).

This codebase is built on top of RFN-Nest.