ReTD: Reconstruction-Based Traceability Detection for Generated Images
Weizhuo Chen, Fangfang Yuan, Cong Cao, Kun Peng, Dakui Wang, Yanbing Liu
Abstract
The objective of generated image traceability is to accurately identify and locate the source models. In this paper, we propose ReTD (Reconstruction-Based Traceability Detection), a generalized model for generated image traceability detection. Firstly, we use VAE to reconstruct images which are compared with the original ones to extract numerical distinguishing features. Secondly, we use Vision Transformer to learn the fine-grained distribution features to realize the generated image traceability classification. Finally, we conduct traceability experiments using images generated by ten GAN and Diffusion models. The experimental results demonstrate that ReTD only training a unified classifier improves accuracy by 9.4% compared to the state-of-the-art method. The ReTD-related code is availble at https://github.com/chenweizhuo/ReTD.
BibTeX
@inproceedings{icassp2025_retdreconstructi,
title = {ReTD: Reconstruction-Based Traceability Detection for Generated Images},
author = {Weizhuo Chen and Fangfang Yuan and Cong Cao and Kun Peng and Dakui Wang and Yanbing Liu},
booktitle = {ICASSP 2025},
year = {2025}
}