TY - GEN
T1 - DeepfakeUCL
T2 - 2021 International Joint Conference on Neural Networks, IJCNN 2021
AU - Fung, Sheldon
AU - Lu, Xuequan
AU - Zhang, Chao
AU - Li, Chang Tsun
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/18
Y1 - 2021/7/18
N2 - Face deepfake detection has seen impressive results recently. Nearly all existing deep learning techniques for face deepfake detection are fully supervised and require labels during training. In this paper, we design a novel deepfake detection method via unsupervised contrastive learning. We first generate two different transformed versions of an image and feed them into two sequential sub-networks, i.e., an encoder and a projection head. The unsupervised training is achieved by maximizing the correspondence degree of the outputs of the projection head. To evaluate the detection performance of our unsupervised method, we further use the unsupervised features to train an efficient linear classification network. Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings. We also conduct ablation studies for our method.
AB - Face deepfake detection has seen impressive results recently. Nearly all existing deep learning techniques for face deepfake detection are fully supervised and require labels during training. In this paper, we design a novel deepfake detection method via unsupervised contrastive learning. We first generate two different transformed versions of an image and feed them into two sequential sub-networks, i.e., an encoder and a projection head. The unsupervised training is achieved by maximizing the correspondence degree of the outputs of the projection head. To evaluate the detection performance of our unsupervised method, we further use the unsupervised features to train an efficient linear classification network. Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings. We also conduct ablation studies for our method.
UR - http://www.scopus.com/inward/record.url?scp=85116418834&partnerID=8YFLogxK
U2 - 10.1109/IJCNN52387.2021.9534089
DO - 10.1109/IJCNN52387.2021.9534089
M3 - 会議への寄与
AN - SCOPUS:85116418834
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - IJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 18 July 2021 through 22 July 2021
ER -