Journal ArticleDOI
Inconsistency-Aware Wavelet Dual-Branch Network for Face Forgery Detection
Gengyun Jia,Meisong Zheng,Chuanrui Hu,Xin Ma,Yuting Xu,Luoqi Liu,Yafeng Deng,Ran He +7 more
- Vol. 3, Iss: 3, pp 308-319
TLDR
In this paper, an inconsistency-aware wavelet dual-branch network was proposed for face forgery detection, which is mainly based on two kinds of forgery clues called inter-image and intra-image inconsistencies.Abstract:
Current face forgery techniques can generate high-fidelity fake faces with extremely low labor and time costs. As a result, face forgery detection becomes an important research topic to prevent technology abuse. In this paper, we present an inconsistency-aware wavelet dual-branch network for face forgery detection. This model is mainly based on two kinds of forgery clues called inter-image and intra-image inconsistencies. To fully utilize them, we firstly enhance the forgery features by using additional inputs based on stationary wavelet decomposition (SWD). Then, considering the different properties of the two inconsistencies, we design a dual-branch network that predicts image-level and pixel-level forgery labels respectively. The segmentation branch aims to recognize real and fake local regions, which is crucial for discovering intra-image inconsistency. The classification branch learns to discriminate the real and fake images globally, thus can extract inter-image inconsistency. Finally, bilinear pooling is employed to fuse the features from the two branches. We find that the bilinear pooling is a kind of spatial attentive pooling. It effectively utilizes the rich spatial features learned by the segmentation branch. Experimental results show that the proposed method surpasses the state-of-the-art face forgery detection methods.read more
Citations
More filters
Proceedings ArticleDOI
Visual-Semantic Transformer for Face Forgery Detection
TL;DR: Zhang et al. as mentioned in this paper proposed a visual-semantic transformer (VST) to detect face forgery based on semantic aware feature relations, which achieved 99.58% accuracy on FF++(Raw) and 96.16% on Celeb-DF.
Journal ArticleDOI
Face Forgery Detection Based on the Improved Siamese Network
TL;DR: This work proposes a face forgery detection method that consists of preprocessing, an improved Siamese network-based feature extractor (including a feature alignment module), and postprocessing (a voting principle).
Proceedings ArticleDOI
Learning Second Order Local Anomaly for General Face Forgery Detection
TL;DR: A weakly supervised Second Order Local Anomaly (SOLA) learning module to mine anomalies in local regions using deep feature maps and an improved Adaptive Spatial Rich Model (ASRM) is introduced to help mine subtle noise features via learnable high pass filters.
Journal ArticleDOI
A Survey on Learning to Reject
TL;DR: In this paper , the authors present a comprehensive overview of self-awareness in machine learning from three perspectives: confidence, calibration, and discrimination, and provide a general taxonomy, organization, and discussion of the methods for solving these problems.
Journal ArticleDOI
Patch-DFD: Patch-based end-to-end DeepFake discriminator
TL;DR: Wang et al. as discussed by the authors proposed a patch-based solution of Facial Patch Mapping (FPM) to obtain several part-based feature maps, preserving original details of each facial patch to the greatest extent.
References
More filters
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Journal ArticleDOI
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
TL;DR: Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet.
Proceedings ArticleDOI
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
TL;DR: CycleGAN as discussed by the authors learns a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss.
Proceedings ArticleDOI
Xception: Deep Learning with Depthwise Separable Convolutions
TL;DR: This work proposes a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions, and shows that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset, and significantly outperforms it on a larger image classification dataset.