MSU-Net: the multi-scale supervised U-Net for image splicing forgery localization

Image splicing forgery, that is, copying some parts of an image into another image, is one of the frequently used tampering methods in image forgery. As a research hotspot in recent years, deep learning has been used in image forgery detection. However, current deep learning methods have two drawbacks: first, they are too simple in feature fusion; second, they rely only on a single cross-entropy loss as the loss function, leading to models prone to overfitting. To address these issues, a image splicing forgery localization method based on multi-scale supervised U-shaped network, named MSU-Net, is proposed in this paper. First, a triple-stream feature extraction module is designed, which combines the noise view and edge information of the input image to extract semantic-related and semantic-agnostic features. Second, a feature hierarchical fusion mechanism is proposed that introduces a channel attention mechanism layer by layer to perceive multi-level manipulation trajectories, avoiding the loss of information in semantic-related and semantic-agnostic shallow features during the convolution process. Finally, a strategy for multi-scale supervision is developed, a boundary artifact localization module is designed to compute the edge loss, and a contrastive learning module is introduced to compute the contrastive loss. Through extensive experiments on several public datasets, MSU-Net demonstrates high accuracy in localizing tampered regions and outperforms state-of-the-art methods. Additional attack experiments show that MSU-Net exhibits good robustness against Gaussian blur, Gaussian noise, and JPEG compression attacks. Besides, MSU-Net is superior in terms of model complexity and localization speed.