U2-Net for Image Forgery Detection and Localization

Until now, image forgery has caused great harm in many aspects, such as certificate falsification, fake news, Internet rumors. As a result, the algorithm for image forensics is of great importance. Existing image forensics algorithms are mature in image forgery detection. Nevertheless, there is still room for improvement when it comes to image forgery localization. This paper modified and migrated U
²
-Net to image forensics, and conducted several experiments to demonstrate the effectiveness of U
²
-Net in contrast to ManTra-Net. The experimental results demonstrate that U
²
-Net is not only capable of image forgery detection but also image forgery localization and that in some cases U
²
-Net is even more powerful than ManTra-Net in image forgery localization.