Skip to content

Latest commit

 

History

History
48 lines (42 loc) · 1.32 KB

README.md

File metadata and controls

48 lines (42 loc) · 1.32 KB

Image Forgery Localization with State Space Models

An official implementation code for paper "Image Forgery Localization with State Space Models.". This repo provides code and trained weights.

Framework

Dependency

  • torch 1.13.1+cu117
  • torchvision 0.14.1+cu117
  • python 3.10
  • causal-conv1d 1.0.0
  • mamba-ssm 1.0.1
  • selective_scan 0.0.2

Installation

Please refer to the installation of VMamba

Usage

For example to train:

cd LoMa/models
python generate_npy.py
python train.py

For example to test: download LoMa.pth

cd LoMa/models
python generate_npy.py
python test.py

Citation

If you use this code for your research, please cite our paper

@article{lou2025image,
  title={Image Forgery Localization with State Space Models},
  author={Lou, Zijie and Cao, Gang and Guo, Kun and Weng, Shaowei and Yu, Lifang},
  journal={IEEE Signal Processing Letters},
  year={2025}
}

License

Licensed under a Creative Commons Attribution-NonCommercial 4.0 International for Non-commercial use only. Any commercial use should get formal permission first.