Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learning

With the rapid development of facial forgery techniques, forgery detection has attracted more and more attention due to security concerns. Existing approaches attempt to use frequency information to mine subtle artifacts under high-quality forged faces. However, the exploitation of frequency information is coarse-grained, and more importantly, their vanilla learning process struggles to extract fine-grained forgery traces. To address this issue, we propose a progressive enhancement learning framework to exploit both the RGB and fine-grained frequency clues. Specifically, we perform a fine-grained decomposition of RGB images to completely decouple the real and fake traces in the frequency space. Subsequently, we propose a progressive enhancement learning framework based on a two-branch network, combined with self-enhancement and mutual-enhancement modules. The self-enhancement module captures the traces in different input spaces based on spatial noise enhancement and channel attention. The Mutual-enhancement module concurrently enhances RGB and frequency features by communicating in the shared spatial dimension. The progressive enhancement process facilitates the learning of discriminative features with fine-grained face forgery clues. Extensive experiments on several datasets show that our method outperforms the state-of-the-art face forgery detection methods.

[1]  Kai Xu,et al.  Learning in the Frequency Domain , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jessica J. Fridrich,et al.  Rich Models for Steganalysis of Digital Images , 2012, IEEE Transactions on Information Forensics and Security.

[3]  Junichi Yamagishi,et al.  Distinguishing computer graphics from natural images using convolution neural networks , 2017, 2017 IEEE Workshop on Information Forensics and Security (WIFS).

[4]  Lizhuang Ma,et al.  Face Manipulation Detection via Auxiliary Supervision , 2020, ICONIP.

[5]  Yongdong Zhang,et al.  Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Yu-Gang Jiang,et al.  WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection , 2020, ACM Multimedia.

[7]  Junchi Yan,et al.  Generalizing Face Forgery Detection with High-frequency Features , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Siwei Lyu,et al.  In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking , 2018, 2018 IEEE International Workshop on Information Forensics and Security (WIFS).

[9]  Jian Yang,et al.  DSFD: Dual Shot Face Detector , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Justus Thies,et al.  Deferred Neural Rendering: Image Synthesis using Neural Textures , 2019 .

[11]  Erhard Taverna Deepfakes , 2019, Bulletin des Médecins Suisses.

[12]  Fang Wen,et al.  FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping , 2019, ArXiv.

[13]  Hui Ding,et al.  Learning to Recognize Patch-Wise Consistency for Deepfake Detection , 2020, ArXiv.

[14]  Christian Riess,et al.  Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations , 2019, 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW).

[15]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[16]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Belhassen Bayar,et al.  A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer , 2016, IH&MMSec.

[18]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Junichi Yamagishi,et al.  MesoNet: a Compact Facial Video Forgery Detection Network , 2018, 2018 IEEE International Workshop on Information Forensics and Security (WIFS).

[20]  Junichi Yamagishi,et al.  Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos , 2019, 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[21]  Baining Guo,et al.  Face X-Ray for More General Face Forgery Detection , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[23]  Xin Yang,et al.  Exposing Deep Fakes Using Inconsistent Head Poses , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[24]  Rongrong Ji,et al.  Local Relation Learning for Face Forgery Detection , 2021, AAAI.

[25]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Nenghai Yu,et al.  Multi-attentional Deepfake Detection , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Asja Fischer,et al.  Leveraging Frequency Analysis for Deep Fake Image Recognition , 2020, ICML.

[28]  Lu Sheng,et al.  Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues , 2020, ECCV.

[29]  CNN-based Multiple Manipulation Detector Using Frequency Domain Features of Image Residuals , 2020, ACM Trans. Intell. Syst. Technol..

[30]  Andreas Rössler,et al.  FaceForensics++: Learning to Detect Manipulated Facial Images , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[31]  Davide Cozzolino,et al.  Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detection , 2017, IH&MMSec.

[32]  Lizhuang Ma,et al.  Spatiotemporal Inconsistency Learning for DeepFake Video Detection , 2021, ACM Multimedia.

[33]  Cristian Canton Ferrer,et al.  The DeepFake Detection Challenge (DFDC) Dataset. , 2020 .

[34]  Feng Liu,et al.  On the Detection of Digital Face Manipulation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).