Learn with diversity and from harder samples: Improving the generalization of CNN-Based detection of computer-generated images

Quan, Weize; Wang, Kai; Yan, Dong‐Ming; Zhang, Xiao-Peng; Pellerin, Denis

doi:10.1016/j.fsidi.2020.301023

Cited by 12 publications

(56 citation statements)

References 23 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new end-to-end CNN architecture called selfcoding network (ScNet) was constructed with introducing hybrid correlation module and combining with existing CNN model to enhance the discrimination ability and application generality. Quan et al [28] pointed out that the problem of blind detection of CG images is ignored in existing CNN-based methods, i.e., it is unknown whether the training images is generated by computer rendering tools or not for detection training. In order to improve the generalization ability of the model, a dual-branch neural network was designed to capture diverse features.…”

Section: Methods Based On Deepmentioning

confidence: 99%

An Improved Self-Training Model with Fine-Tuning Teacher/Student Exchange Strategy to Detect Computer-Generated Images

Yao

Liu

Wang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

Computer-generated (CG) images have become indistinguishable from natural images due to powerful image rendering technology. Fake CG images have brought huge troubles to news media, judicial forensics, and other fields. How to detect CG image has become a key point to solve the problems mentioned above. The image classification method based on deep learning, due to its strong self-learning ability, can automatically determine the differences in the image features between CG images and natural images and can be used to detect CG images. However, deep learning often requires a large amount of labeled data, which is usually a tedious and complex task. This paper proposes an improved self-training strategy with fine-tuning teacher/student exchange (FTTSE) to solve the problem of missing labeled datasets. Our method is actually a strategy based on semisupervised learning to train the teacher model through labeled data and to predict the unlabeled data by the teacher model to generate pseudo labels. The student model is obtained by continuous training on the mixed dataset composed of labeled and pseudo-labeled data. A teacher/student exchange strategy is designed for iterative training; i.e., the identities of the teacher model and the student model are exchanged at the beginning of each round of iteration. And then the new teacher model is used to predict pseudo labels, and the new student model exchanged from teacher model in the previous round of iteration is fine-tuned and retrained by the mixed dataset with new pseudo labels. Furthermore, we introduced malicious image attacks to perturb the mixed dataset to improve the robustness of the student model. The experimental results show that the improved self-training model we proposed can stably maintain the image classification ability even if the testing images are maliciously attacked. After iterative training, the CG image detection accuracy of the final model increases by 5.18%. The robustness against 100% malicious attacks is also improved, where the final trained model has an accuracy improvement of 7.63% higher than the initial model. The self-training model with FTTSE strategy proposed in this paper can effectively enhance the detection ability of the existing model and can greatly improve the robustness of the model with iterative training.

show abstract

Section: Methods Based On Deepmentioning

confidence: 99%

An Improved Self-Training Model with Fine-Tuning Teacher/Student Exchange Strategy to Detect Computer-Generated Images

Yao

Liu

Wang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…A baseline texture-aware network was proposed to address the discrimination problem on their benchmark dataset. A novel two-branch network was proposed to tackle the generalization problem in the blind detection of CGIs by introducing different initializations in the first layer so that more diverse features were extracted [20]. However, no prior knowledge of new distributions was used to develop a rigorous formulation.…”

Section: Related Workmentioning

confidence: 99%

“…Distinguishing CGIs from NIs can be treated as a classification task. Until recently, many approaches have proposed hand-crafted features [14][15][16][17][18] to cope with the aforementioned classification problem, while the majority of recent state-of-the-art methods utilize deep neural network (DNN) methods, e.g., [19][20][21][22][23][24]. The latter methods tend to be more efficient in discovering hidden patterns and structures in images.…”

Section: Introductionmentioning

confidence: 99%

Detect with Style: A Contrastive Learning Framework for Detecting Computer-Generated Images

Karantaidis,

Kotropoulos

2024

Information

View full text Add to dashboard Cite

The detection of computer-generated (CG) multimedia content has become of utmost importance due to the advances in digital image processing and computer graphics. Realistic CG images could be used for fraudulent purposes due to the deceiving recognition capabilities of human eyes. So, there is a need to deploy algorithmic tools for distinguishing CG images from natural ones within multimedia forensics. Here, an end-to-end framework is proposed to tackle the problem of distinguishing CG images from natural ones by utilizing supervised contrastive learning and arbitrary style transfer by means of a two-stage deep neural network architecture. This architecture enables discrimination by leveraging per-class embeddings and generating multiple training samples to increase model capacity without the need for a vast amount of initial data. Stochastic weight averaging (SWA) is also employed to improve the generalization and stability of the proposed framework. Extensive experiments are conducted to investigate the impact of various noise conditions on the classification accuracy and the proposed framework’s generalization ability. The conducted experiments demonstrate superior performance over the existing state-of-the-art methodologies on the public DSTok, Rahmouni, and LSCGB benchmark datasets. Hypothesis testing asserts that the improvements in detection accuracy are statistically significant.

show abstract

“…Interestingly, the inputs for this network were pre-processed by a Gaussian low-pass filter as the authors wanted to focus on general patterns rather than local details. Quan et al [ 143 ] designed a CNN combining SRM filters and Gaussian random weights as initializations for the first layer on a two-branch architecture. The authors also proposed to use the so-called negative samples created via gradient-based distortion to achieve a better generalization on test images created by unknown graphics rendering engines.…”

Section: Other Specific Forensic Problemsmentioning

confidence: 99%

A Comprehensive Review of Deep-Learning-Based Methods for Image Forensics

Camacho

Wang

2021

J. Imaging

Self Cite

View full text Add to dashboard Cite

Seeing is not believing anymore. Different techniques have brought to our fingertips the ability to modify an image. As the difficulty of using such techniques decreases, lowering the necessity of specialized knowledge has been the focus for companies who create and sell these tools. Furthermore, image forgeries are presently so realistic that it becomes difficult for the naked eye to differentiate between fake and real media. This can bring different problems, from misleading public opinion to the usage of doctored proof in court. For these reasons, it is important to have tools that can help us discern the truth. This paper presents a comprehensive literature review of the image forensics techniques with a special focus on deep-learning-based methods. In this review, we cover a broad range of image forensics problems including the detection of routine image manipulations, detection of intentional image falsifications, camera identification, classification of computer graphics images and detection of emerging Deepfake images. With this review it can be observed that even if image forgeries are becoming easy to create, there are several options to detect each kind of them. A review of different image databases and an overview of anti-forensic methods are also presented. Finally, we suggest some future working directions that the research community could consider to tackle in a more effective way the spread of doctored images.

show abstract

Learn with diversity and from harder samples: Improving the generalization of CNN-Based detection of computer-generated images

Cited by 12 publications

References 23 publications

An Improved Self-Training Model with Fine-Tuning Teacher/Student Exchange Strategy to Detect Computer-Generated Images

An Improved Self-Training Model with Fine-Tuning Teacher/Student Exchange Strategy to Detect Computer-Generated Images

Detect with Style: A Contrastive Learning Framework for Detecting Computer-Generated Images

A Comprehensive Review of Deep-Learning-Based Methods for Image Forensics

Contact Info

Product

Resources

About