Laser & Optoelectronics Progress, Volume. 60, Issue 10, 1015001(2023)
Deepfake Detection Algorithm for High-Frequency Components of Shallow Features
Fig. 1. Overall architecture of deepfake detection algorithm for high-frequency components of shallow features
Fig. 2. Module structure of high-frequency information residual extraction
Fig. 3. Spectrogram comparison. (a) Original image; (b) image from residual extraction module; (c) image from Laplace filter
Fig. 4. Structure of CBAM
Fig. 5. Structure of high-frequency information enhancement module
Fig. 6. Effect before and after enhancement of high-frequency feature map corresponding to real and fake samples. (a) (b) Original images
Fig. 7. Template for Laplace operator
Fig. 8. Feature map variations. (a) Shallow feature maps
Fig. 9. Spectrogram variations. (a) Shallow feature maps
Fig. 10. Variation of model Acc index with the number of network layers on 3 datasets
Fig. 11. Variation of model AUC index with the number of network layers on 3 datasets
Fig. 12. Line graph of change in average Acc index with
Fig. 13. Line graph of change in average AUC index with
Fig. 14. Comparison of average Acc on three datasets after introduction of GC
Fig. 15. Comparison of average loss on three datasets after introduction of GC
|
|
|
|
|
|
Get Citation
Copy Citation Text
Shufan Peng, Manchun Cai, Rui Ma, Xiaowen Liu. Deepfake Detection Algorithm for High-Frequency Components of Shallow Features[J]. Laser & Optoelectronics Progress, 2023, 60(10): 1015001
Category: Machine Vision
Received: Dec. 23, 2021
Accepted: Feb. 14, 2022
Published Online: May. 17, 2023
The Author Email: Cai Manchun (caimanchun@ppsuc.edu.cn)