Exploiting Fine-Grained Face Forgery Clues via Progressive Enhancement Learning


  • Qiqi Gu Shanghai Jiao Tong University Tencent YouTu Lab
  • Shen Chen Tencent YouTu Lab
  • Taiping Yao Tencent YouTu
  • Yang Chen Tencent
  • Shouhong Ding Tencent
  • Ran Yi Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence, SJTU




Computer Vision (CV)


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.




How to Cite

Gu, Q., Chen, S., Yao, T., Chen, Y., Ding, S., & Yi, R. (2022). Exploiting Fine-Grained Face Forgery Clues via Progressive Enhancement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 735-743. https://doi.org/10.1609/aaai.v36i1.19954



AAAI Technical Track on Computer Vision I