Hierarchical Progressive Image Forgery Detection and Localization Method Based on UNet-Reference-Cited by-同舟云学术

Hierarchical Progressive Image Forgery Detection and Localization Method Based on UNet

Published:2024-09-10 Issue:9 Volume:8 Page:119
ISSN:2504-2289
Container-title:Big Data and Cognitive Computing
language:en
Short-container-title:BDCC

Author:

Liu Yang¹^ORCID,Li Xiaofei¹,Zhang Jun¹,Li Shuohao¹,Hu Shengze¹,Lei Jun¹

Affiliation:

1. Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410000, China

Abstract

The rapid development of generative technologies has made the production of forged products easier, and AI-generated forged images are increasingly difficult to accurately detect, posing serious privacy risks and cognitive obstacles to individuals and society. Therefore, constructing an effective method that can accurately detect and locate forged regions has become an important task. This paper proposes a hierarchical and progressive forged image detection and localization method called HPUNet. This method assigns more reasonable hierarchical multi-level labels to the dataset as supervisory information at different levels, following cognitive laws. Secondly, multiple types of features are extracted from AI-generated images for detection and localization, and the detection and localization results are combined to enhance the task-relevant features. Subsequently, HPUNet expands the obtained image features into four different resolutions and performs detection and localization at different levels in a coarse-to-fine cognitive order. To address the limited feature field of view caused by inconsistent forgery sizes, we employ three sets of densely cross-connected hierarchical networks for sufficient interaction between feature images at different resolutions. Finally, a UNet network with a soft-threshold-constrained feature enhancement module is used to achieve detection and localization at different scales, and the reliance on a progressive mechanism establishes relationships between different branches. We use ACC and F1 as evaluation metrics, and extensive experiments on our method and the baseline methods demonstrate the effectiveness of our approach.

Funder

Laboratory of Big Data and Decision Making of National University of Defense Technology

Publisher

MDPI AG

Link

https://www.mdpi.com/2504-2289/8/9/119/pdf

Reference47 articles.

1. Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., Mosseri, I., and Irani, M. (2023, January 17–24). Imagic: Text-based real image editing with diffusion models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.

2. Manukyan, H., Sargsyan, A., Atanyan, B., Wang, Z., Navasardyan, S., and Shi, H. (2023). Hd-painter: High-resolution and prompt-faithful text-guided image inpainting with diffusion models. arXiv.

3. Bar-Tal, O., Yariv, L., Lipman, Y., and Dekel, T. (2023, January 23–29). Multidiffusion: Fusing diffusion paths for controlled image generation. Proceedings of the ICML’23: International Conference on Machine Learning, Honolulu, HI, USA.

4. Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv.

5. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. Adv. Neural Inf. Process. Syst., 27.