CORE: Consistent Representation Learning for Face Forgery Detection

Ni, Yunsheng; Meng, Depu; Yu, Changqian; Quan, Chengbin; Ren, Dongchun; Zhao, Youjian

doi:10.1109/cvprw56347.2022.00011

Cited by 22 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…COnsistency REpresentation Learning of Forgery Detection (CORE) [27] is an effective network that can capture different representations between two data augmentations and regularize feature similarity by the cosine distance to enhance consistency so that it can achieve relatively good results in both in-dataset and cross-dataset evaluation. We acknowledge that traditional classifiers always follow the steps of data augmentation, extracting and encoding features, and fully connected layers to achieve classification tasks.…”

Section: Consistency Representation Learningmentioning

confidence: 99%

A Contemporary Survey on Deepfake Detection: Datasets, Algorithms, and Challenges

Gong,

2024

Electronics

View full text Add to dashboard Cite

Deepfakes are notorious for their unethical and malicious applications to achieve economic, political, and social reputation goals. Recent years have seen widespread facial forgery, which does not require technical skills. Since the development of generative adversarial networks (GANs) and diffusion models (DMs), deepfake generation has been moving toward better quality. Therefore, it is necessary to find an effective method to detect fake media. This contemporary survey provides a comprehensive overview of several typical facial forgery detection methods proposed from 2019 to 2023. We also analyze and group them into four categories in terms of their feature extraction methods and network architectures: traditional convolutional neural network (CNN)-based detection, CNN backbone with semi-supervised detection, transformer-based detection, and biological signal detection. Furthermore, it summarizes several representative deepfake detection datasets with their advantages and disadvantages. Finally, we evaluate the performance of these detection models with respect to different datasets by comparing their evaluating metrics. Across all experimental results on these state-of-the-art detection models, we find that the accuracy is largely degraded if we utilize cross-dataset evaluation. These results will provide a reference for further research to develop more reliable detection algorithms.

show abstract

Section: Consistency Representation Learningmentioning

confidence: 99%

A Contemporary Survey on Deepfake Detection: Datasets, Algorithms, and Challenges

Gong,

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Although the scope of this survey is on the detection of GAN-based entire face synthesis, the GAN-face detection task is closely related to other fake face detection tasks [82,25]. For completeness, we also discuss other surveys in the related fields.…”

Section: Related Surveysmentioning

confidence: 99%

GAN-Generated Faces Detection: A Survey and New Perspectives

Wang,

Guo,

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Generative Adversarial Networks (GAN) have led to the generation of very realistic face images, which have been used in fake social media accounts and other disinformation matters that can generate profound impacts. Therefore, the corresponding GAN-face detection techniques are under active development that can examine and expose such fake faces. In this work, we aim to provide a comprehensive review of recent progress in GAN-face detection. We focus on methods that can detect face images that are generated or synthesized from GAN models. We classify the existing detection works into four categories: (1) deep learning-based, (2) physical-based, (3) physiological-based methods, and (4) evaluation and comparison against human visual performance. For each category, we summarize the key ideas and connect them with method implementations. We also discuss open problems and suggest future research directions.

show abstract

“…Qian et al [25] utilized frequency-aware decomposed-image components and local frequency statistics, in face-forgery detection Luo et al [26] proposed utilizing high-frequency features for detection by combining models such as a multi-scale high-frequency feature-extraction module and a residual-guided spatial-attention module. Ni [8] proposed consistent representation learning (CORE), which constrains the consistency of different representations. The method based on the different representations is first captured with different augmentations, and then the cosine distance of the representations is regularized, to enhance consistency.…”

Section: Related Workmentioning

confidence: 99%

“…Meanwhile, some other methods [3,4] put main emphasis on CNN models to extract synthetic trace-features and detect the superimposed noise generated during the synthesis process [5][6][7]. Recently, Ni et al [8] proposed a detection method based on consistent representation learning by capturing the different representations with different augmentations and calculating the distance for the different representations. Wang et al [9] proposed to combine the color domain and frequency domain, using a frequency-domain filter-based multi-scale transformer.…”

Section: Introductionmentioning

confidence: 99%

A Transformer-Based DeepFake-Detection Method for Facial Organs

et al. 2022

View full text Add to dashboard Cite

Nowadays, deepfake detection on subtle-expression manipulation, facial-detail modification, and smeared images has become a research hotspot. Existing deepfake-detection methods on the whole face are coarse-grained, where the details are missing due to the negligible manipulated size of the image. To address the problems, we propose to build a transformer model for a deepfake-detection method by organ, to obtain the deepfake features. We reduce the detection weight of defaced or unclear organs to prioritize the detection of clear and intact organs. Meanwhile, to simulate the real-world environment, we build a Facial Organ Forgery Detection Test Dataset (FOFDTD), which includes the images of mask face, sunglasses face, and undecorated face collected from the network. Experimental results on four benchmarks, i.e., FF++, DFD, DFDC-P, Celeb-DF, and for FOFDTD datasets, demonstrated the effectiveness of our proposed method.

show abstract

CORE: Consistent Representation Learning for Face Forgery Detection

Cited by 22 publications

References 39 publications

A Contemporary Survey on Deepfake Detection: Datasets, Algorithms, and Challenges

A Contemporary Survey on Deepfake Detection: Datasets, Algorithms, and Challenges

GAN-Generated Faces Detection: A Survey and New Perspectives

A Transformer-Based DeepFake-Detection Method for Facial Organs

Contact Info

Product

Resources

About