FaceForensics Benchmark
This table lists the benchmark results for the Binary Classification scenario.
Method | Info | Deepfakes | Face2Face | FaceSwap | NeuralTextures | Pristine | Total |
---|---|---|---|---|---|---|---|
![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ||
ZAntiFakeBio | 1.000 | 0.920 | 0.971 | 0.907 | 0.936 | 0.940 | |
Leo | 1.000 | 0.861 | 0.971 | 0.853 | 0.922 | 0.917 | |
NoSenseAtAll | 0.982 | 0.905 | 0.951 | 0.827 | 0.908 | 0.908 | |
Cancer | 0.964 | 0.781 | 0.942 | 0.780 | 0.952 | 0.903 | |
RobustForensics | 0.991 | 0.891 | 0.951 | 0.807 | 0.904 | 0.902 | |
Aquarius | 1.000 | 0.854 | 0.971 | 0.807 | 0.884 | 0.890 | |
PredictFake | 0.973 | 0.847 | 0.913 | 0.820 | 0.894 | 0.887 | |
StableForensics | 0.991 | 0.847 | 0.951 | 0.787 | 0.884 | 0.883 | |
FAKEDET | 0.964 | 0.832 | 0.922 | 0.687 | 0.918 | 0.877 | |
ATDETECTOR | 0.955 | 0.796 | 0.922 | 0.780 | 0.898 | 0.875 | |
InTeLe_ | 1.000 | 0.796 | 0.922 | 0.720 | 0.884 | 0.864 | |
Balance | 0.918 | 0.861 | 0.883 | 0.733 | 0.876 | 0.858 | |
CONG | 0.955 | 0.810 | 0.854 | 0.780 | 0.874 | 0.858 | |
Firefly | 0.955 | 0.730 | 0.874 | 0.667 | 0.920 | 0.855 | |
AllDataRes_EB5 | 0.964 | 0.818 | 0.845 | 0.647 | 0.900 | 0.852 | |
LGSC_Lite | 0.955 | 0.839 | 0.874 | 0.773 | 0.844 | 0.848 | |
KBNet | 0.909 | 0.774 | 0.854 | 0.793 | 0.852 | 0.839 | |
ZFake | 0.945 | 0.737 | 0.864 | 0.693 | 0.880 | 0.838 | |
EfficientB5_OHEM | 0.918 | 0.876 | 0.913 | 0.653 | 0.848 | 0.837 | |
UltraVision | 0.918 | 0.847 | 0.932 | 0.733 | 0.810 | 0.828 | |
focbe | 0.900 | 0.832 | 0.786 | 0.793 | 0.828 | 0.827 | |
Xceptio InceptionRes Efficient | 0.964 | 0.825 | 0.864 | 0.827 | 0.768 | 0.816 | |
fakeface | 0.955 | 0.766 | 0.883 | 0.747 | 0.806 | 0.816 | |
IR+unet | 0.909 | 0.847 | 0.845 | 0.787 | 0.790 | 0.816 | |
EffB7_DataAug_v7 | 0.964 | 0.920 | 0.951 | 0.867 | 0.710 | 0.815 | |
RealFace | 0.945 | 0.766 | 0.864 | 0.813 | 0.790 | 0.815 | |
unet+res | 0.882 | 0.832 | 0.796 | 0.767 | 0.812 | 0.814 | |
Inception Resnet V1 | ![]() | 0.936 | 0.839 | 0.903 | 0.820 | 0.750 | 0.809 |
Nika Dogonadze, Jana Obernosterer: Deep Face Forgery Detection. Advanced Deep Learning for Computer Vision Course at TUM | |||||||
faceClassify1 | 0.945 | 0.854 | 0.981 | 0.793 | 0.730 | 0.806 | |
yd dust face | 0.955 | 0.861 | 0.951 | 0.693 | 0.762 | 0.806 | |
Yolo with Voting Mechanism | 0.855 | 0.606 | 0.709 | 0.587 | 0.916 | 0.796 | |
antifake | 0.936 | 0.803 | 0.942 | 0.687 | 0.764 | 0.795 | |
Yolo Object detection | 0.864 | 0.628 | 0.757 | 0.667 | 0.854 | 0.786 | |
EfficientB4_380 | 0.882 | 0.701 | 0.796 | 0.740 | 0.794 | 0.783 | |
EffB7_DataAug_v1 | 0.945 | 0.847 | 0.825 | 0.813 | 0.712 | 0.783 | |
EfficientNet-b4 | 0.955 | 0.796 | 0.825 | 0.827 | 0.712 | 0.779 | |
framelevel | 0.873 | 0.737 | 0.835 | 0.760 | 0.760 | 0.777 | |
swap_classify | 0.909 | 0.759 | 0.864 | 0.747 | 0.724 | 0.767 | |
SCAN | ![]() | 0.909 | 0.825 | 0.738 | 0.613 | 0.764 | 0.763 |
Sentinel | 0.964 | 0.905 | 0.883 | 0.867 | 0.624 | 0.763 | |
face single model | 0.964 | 0.869 | 0.942 | 0.460 | 0.738 | 0.760 | |
HKU_EfficientNet-B7_v2 | 0.845 | 0.606 | 0.806 | 0.447 | 0.864 | 0.758 | |
HRC | 0.827 | 0.613 | 0.573 | 0.660 | 0.848 | 0.757 | |
FullEfficientNet | 0.836 | 0.526 | 0.728 | 0.480 | 0.880 | 0.751 | |
simple policy | ![]() | 0.955 | 0.869 | 0.942 | 0.387 | 0.744 | 0.751 |
LVLNet | 0.964 | 0.752 | 0.796 | 0.687 | 0.694 | 0.741 | |
EfficientNetB7 | 0.836 | 0.847 | 0.874 | 0.747 | 0.630 | 0.725 | |
DFirt | 0.982 | 0.942 | 0.961 | 0.893 | 0.494 | 0.717 | |
Xception | ![]() | 0.964 | 0.869 | 0.903 | 0.807 | 0.524 | 0.710 |
Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner: FaceForensics++: Learning to Detect Manipulated Facial Images. ICCV 2019 | |||||||
EfficientNet-b7-Attention | 0.955 | 0.803 | 0.854 | 0.600 | 0.616 | 0.701 | |
eff-b7-att epc11 | 0.955 | 0.788 | 0.864 | 0.547 | 0.592 | 0.680 | |
MesoNet | 0.873 | 0.562 | 0.612 | 0.407 | 0.726 | 0.660 | |
Darius Afchar, Vincent Nozick, Junichi Yamagishi, and Isao Echizen: Mesonet: a compact facial video forgery detection network. arXiv | |||||||
IAMFAKE2 | 0.464 | 0.496 | 0.515 | 0.367 | 0.826 | 0.640 | |
PPPP | 0.827 | 0.635 | 0.621 | 0.480 | 0.628 | 0.628 | |
GAEL-Net | 0.718 | 0.686 | 0.631 | 0.707 | 0.562 | 0.625 | |
Jae-Yong Baek, Yong-Sang Yoo, Seung-Hwan Bae: Generative Adversarial Ensemble Learning for Face Forensics. IEEE Access | |||||||
XceptionNet Full Image | ![]() | 0.745 | 0.759 | 0.709 | 0.733 | 0.510 | 0.624 |
Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner: FaceForensics++: Learning to Detect Manipulated Facial Images. ICCV 2019 | |||||||
resnet50 | 0.527 | 0.504 | 0.408 | 0.387 | 0.786 | 0.620 | |
p-DARTS, generalized-cells | 0.791 | 0.730 | 0.816 | 0.720 | 0.478 | 0.618 | |
Jordi Moreno: Progressive Differentiable Architecture Search for DeepFake Detection. MSc Research Project, from Upf | |||||||
Bayar and Stamm | 0.845 | 0.737 | 0.825 | 0.707 | 0.462 | 0.616 | |
Belhassen Bayar and Matthew C. Stamm: A deep learning approach to universal image manipulation detection using a new convolutional layer. ACM Workshop on Information Hiding and Multimedia Security | |||||||
IAMFAKE | 0.436 | 0.409 | 0.524 | 0.300 | 0.816 | 0.611 | |
inceptionv1 | 0.655 | 0.350 | 0.544 | 0.333 | 0.768 | 0.610 | |
Yjz | 0.445 | 0.372 | 0.505 | 0.160 | 0.856 | 0.604 | |
EfficientNetTest | 0.709 | 0.445 | 0.631 | 0.387 | 0.674 | 0.599 | |
Forged face detection : fCNN | 0.791 | 0.642 | 0.709 | 0.513 | 0.544 | 0.597 | |
Rahmouni | 0.855 | 0.642 | 0.563 | 0.607 | 0.500 | 0.581 | |
Nicolas Rahmouni, Vincent Nozick, Junichi Yamagishi, and Isao Echizen: Distinguishing computer graphics from natural images using convolution neural networks. IEEE Workshop on Information Forensics and Security, | |||||||
framelevel_all_compress_format | 0.782 | 0.124 | 0.155 | 0.173 | 0.860 | 0.575 | |
EfficientNet-v0 | 0.827 | 0.730 | 0.806 | 0.533 | 0.420 | 0.564 | |
Two-stream-SRM-RGB1 | 0.982 | 0.927 | 0.942 | 0.953 | 0.174 | 0.562 | |
Recasting | 0.855 | 0.679 | 0.738 | 0.780 | 0.344 | 0.552 | |
Davide Cozzolino, Giovanni Poggi, and Luisa Verdoliva: Recasting residual-based local descriptors as convolutional neural networks: an application to image forgery detection. ACM Workshop on Information Hiding and Multimedia Security | |||||||
eff-b7-v3 | 0.973 | 0.912 | 0.913 | 0.807 | 0.198 | 0.546 | |
Steganalysis Features | 0.736 | 0.737 | 0.689 | 0.633 | 0.340 | 0.518 | |
Jessica Fridrich and Jan Kodovsky: Rich Models for Steganalysis of Digital Images. IEEE Transactions on Information Forensics and Security | |||||||
YSNet | 0.564 | 0.584 | 0.592 | 0.427 | 0.492 | 0.513 | |