Locate and Verify: A Two-Stream Network for Improved Deepfake Detection
Chao Shuai, Jieming Zhong, Shuang Wu, Feng Dan Lin, Zhibo Wang, Zhongjie Ba, Zhenguang Liu, Lorenzo Cavallaro, Kui Ren · 2023
Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently occurring but relatively unimportant in the training dataset. Furthermore, current methods heavily rely on a few dominant forgery regions and may ignore other equally important regions, leading to inadequate uncovering of forgery cues.