Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection

By Jiaming Li, Hongtao Xie, Jiahong Li, Zhongyuan Wang, Yongdong Zhang. Computer Vision and Pattern Recognition, 2021

345 citations recorded by the source corpus.

Face forgery detection is raising ever-increasing interest in computer vision since facial manipulation technologies cause serious worries. Though recent works have reached sound achievements, there are still unignorable problems: a) learned features supervised by softmax loss are separable but not discriminative enough, since softmax loss does not explicitly encourage intra-class compactness and inter-class separability; and b) fixed filter banks and hand-crafted features are insufficient to capture forgery patterns of frequency from diverse inputs. To compensate for such limitations, a novel frequency-aware discriminative feature learning framework is proposed in this paper. Specifically, we design a novel single-center loss (SCL) that only compresses intra-class variations of natural faces while boosting inter-class differences in the embedding space. In such a case, the network can learn more discriminative features with less optimization difficulty. Besides, an adaptive frequency feature generation module is developed to mine frequency clues in a completely data-driven fashion. With the above two modules, the whole framework can learn more discriminative features in an end-to-end manner. Extensive experiments demonstrate the effectiveness and superiority of our framework on three versions of the FF++ dataset.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3ec60b07eae5c09c4bd9eb93945d0d7c276143a7

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

Citations in the corpus

End-to-End Reconstruction-Classification Learning for Face Forgery Detection (2022, methodology): “[22] take the frequency details into account and propose frequency-aware models to separate bonafide faces and forged faces.”
UCF: Uncovering Common Features for Generalizable Deepfake Detection (2023, background): “To this end, several works [32, 12, 19, 13] utilize frequency information to improve the performance of detectors.”
Detecting Deepfakes with Self-Blended Images (2022, background): “Some studies [23, 37, 43, 44, 50] focus on the frequency domain to capture forgery traces more effectively.”
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection (2022, methodology): “Recent studies have made various attempts for deepfake detection and achieve remarkable success [26, 41, 3, 2, 32, 39, 14, 24, 30, 29, 19, 47, 23, 36, 5].”
Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Domain Learning (2024, methodology): “In response, a multitude of deepfake detection mechanisms have been conceived (Frank et al. 2020; Li et al. 2021), with specific emphasis on detecting facial forgeries.”