Learning Traces by Yourself: Blind Image Forgery Localization via Anomaly Detection With ViT-VAE

Chen, Tong; Li, Bin; Zeng, Jinhua

doi:10.1109/lsp.2023.3245947

Cited by 7 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ding et al 27 proposed DCU-Net, which considers the use of a high-pass filter to extract the residual information of the tampered image used for fusion with RGB features. Chen et al 28 proposed a self-supervised forgery detection method. In the feature extraction phase, their method considers three aspects of feature extraction: noiseprint feature maps, high-pass filtered residual information, and edge feature maps.…”

Section: Forgery Trace Extractionmentioning

confidence: 99%

“…proposed DCU-Net, which considers the use of a high-pass filter to extract the residual information of the tampered image used for fusion with RGB features. Chen et al 28 . proposed a self-supervised forgery detection method.…”

Section: Related Workmentioning

confidence: 99%

“…Most deep learning based forgery detection methods 17 , 27 , 28 , 29 seek to capture more traces of forgery, e.g., they can be from the frequency domain, noise domain, etc. In this paper, more semantic features are extracted from the shallow layer of the network, which contains rich details such as texture, edges, etc., which can be helpful for splicing type of forgery detection.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

End-to-end image splicing localization based on multi-scale features and residual refinement module

Gan,

Jiang,

Chai

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

The addition of objects to the original image in splice forgery results in a change in the semantics of the original image, and distribution of these spliced images may bring negative impacts. To solve this issue, many forgery detection methods based on convolutional neural networks are presented. However, they tend to extract deep features, but ignore the importance of shallow semantics. In addition, the complexity of the forgery localization task leads to insufficient accuracy in detecting smaller forged regions. Based on the above problems, an end-to-end image splicing localization network based on multi-scale features and a residual refinement module (RRM) is proposed in this work. Our approach can be roughly divided into two modules: the detection module and the RRM. First, shallow and deep features are extracted from a backbone network, and deep features are then processed by the deeper atrous spatial pyramid pooling (ASPP) module to extract multi-scale features. The deeper ASPP module uses a smaller dilation rate and light convolution, which is more suitable for detecting complex counterfeit images. Second, the shallow features are fused with the multi-scale features to complement the shallow semantic information, such as texture and edges, which further improve the robustness of the model. Finally, the detection network generates coarse prediction maps that are fed to the RRM, and the RRM optimizes these masks by smoothing the boundaries, filling small gaps, and enhancing the edge details, which improves the pixel-level segmentation results for forgery detection. Extensive experimental results on several public datasets show that this method outperforms other stateof-the-art methods in image forgery localization.

show abstract

Section: Forgery Trace Extractionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

End-to-end image splicing localization based on multi-scale features and residual refinement module

Gan,

Jiang,

Chai

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…However, sophisticated post-processing techniques can destroy the specific tampering traces that such methods may rely on, causing a dramatic decline in the algorithm's performance. Recently, the achievements of deep learning in computer vision [8]- [9] have inspired the development of deep learning-based forgery detection methods [10]- [15], which aim to solve the defect of the classical approaches. Such as Xiao et al [13] employed cascaded coarse-to-refine CNNs to extract discriminative representations.…”

Section: Introductionmentioning

confidence: 99%

Feature Aggregation and Region-Aware Learning for Detection of Splicing Forgery

Xu,

Zheng,

Ren

et al. 2024

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Detection of image splicing forgery become an increasingly difficult task due to the scale variations of the forged areas and the covered traces of manipulation from post-processing techniques. Most existing methods fail to jointly multi-scale local and global information and ignore the correlations between the tampered and real regions in inter-image, which affects the detection performance of multi-scale tampered regions. To tackle these challenges, in this paper, we propose a novel method based on feature aggregation and region-aware learning to detect the manipulated areas with varying scales. In specific, we first integrate multi-level adjacency features using a feature selection mechanism to improve feature representation. Second, a cross-domain correlation aggregation module is devised to perform correlation enhancement of local features from CNN and global representations from Transformer, allowing for a complementary fusion of dualdomain information. Third, a region-aware learning mechanism is designed to improve feature discrimination by comparing the similarities and differences of the features between different regions. Extensive evaluations on benchmark datasets indicate the effectiveness in detecting multi-scale spliced tampered regions.

show abstract