ViXNet: Vision Transformer with Xception Network for deepfakes based video and image forgery detection

Shreyan Ganguly, Aditya Ganguly, Sk Mohiuddin, Samir Malakar, Ram Sarkar

Abstract: Highlights•Proposed a deep learning based model for deepfake image/video detection.•It has a patch-wise self-attention module which learns local image artifacts.•It consists of a vision transformer which learns correlation among masked patches.•Xception based global image features are stacked with patch based local features.•The model achieves good results on some standard video forgery detection datasets.