Local Relation Learning for Face Forgery Detection

By Shen Chen, Taiping Yao, Yang Chen, Shouhong Ding, Jilin Li, Rongrong Ji. AAAI Conference on Artificial Intelligence, 2021

350 citations recorded by the source corpus.

With the rapid development of facial manipulation techniques, face forgery has received considerable attention in digital media forensics due to security concerns. Most existing methods formulate face forgery detection as a classification problem and utilize binary labels or manipulated region masks as supervision. However, without considering the correlation between local regions, these global supervisions are insufficient to learn a generalized feature and prone to overfitting. To address this issue, we propose a novel perspective of face forgery detection via local relation learning. Specifically, we propose a Multi-scale Patch Similarity Module (MPSM), which measures the similarity between features of local regions and forms a robust and generalized similarity pattern. Moreover, we propose an RGB-Frequency Attention Module (RFAM) to fuse information in both RGB and frequency domains for more comprehensive local feature representation, which further improves the reliability of the similarity pattern. Extensive experiments show that the proposed method consistently outperforms the state-of-the-arts on widely-used benchmarks. Furthermore, detailed visualization shows the robustness and interpretability of our method.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/495fe6e707024df0ea547f5a6f135b126a0719f6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Zuxuan Wu
2. Yu-Gang Jiang
3. Chao Ma
4. Luc Van Gool
5. Jingjing Chen
6. Junyi Cao
7. Shen Chen
8. Junke Wang

Citations in the corpus

• End-to-End Reconstruction-Classification Learning for Face Forgery Detection (2022, methodology): “To evaluate our method, we report the most commonly used metrics in related arts [1, 6, 22, 33, 35, 55, 59], including Accuracy (Acc), Area Under the Receiver Operating Characteristic Curve (AUC), and Equal Error Rate (EER).”
• M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection (2021, methodology): “Following [5, 44], we also compute features from the frequency domain to complement RGB features.”