Constrained R-Cnn: A General Image Manipulation Detection Model

@article{Li2020ConstrainedRA,
  title={Constrained R-Cnn: A General Image Manipulation Detection Model},
  author={Huizhou Li and Chao Yang and Fangting Lin and Bin Jiang and Hao-Jun Zhao},
  journal={2020 IEEE International Conference on Multimedia and Expo (ICME)},
  year={2020},
  pages={1-6}
}
Recently, deep learning-based models have exhibited remarkable performance for image manipulation detection. However, most of them suffer from poor universality of handcrafted or predetermined features. Meanwhile, they only focus on manipulation localization and overlook manipulation classification. To address these issues, we propose a coarse-to-fine architecture named Constrained R-CNN for complete and accurate image forensics. First, the learnable manipulation feature extractor learns a… Expand
Image Manipulation Detection by Multi-View Multi-Scale Supervision
TLDR
This paper addresses both aspects of image manipulation detection by multi-view feature learning and multi-scale supervision by exploiting noise distribution and boundary artifact surrounding tampered regions to learn semantic-agnostic and thus more generalizable features. Expand
Hybrid features and semantic reinforcement network for image forgery detection
TLDR
A hybrid features and semantic reinforcement network (HFSRNet) is proposed for image forgery detection, which is an encoding and decoding based network and achieves state-of-the-art performance compared to existing models and baselines. Expand
Inharmonious Region Localization
TLDR
Novel Bi-directional Feature Integration block and Global-context Guided Decoder block are designed to fuse multi-scale features in the encoder and decoder respectively and employ Mask-guided Dual Attention block between the encoding and decoding to suppress the redundant information. Expand
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
TLDR
In this survey, the datasets and methods for the above research directions are summarized and the limitations and potential directions to facilitate the future research for image composition are discussed. Expand
DCU-Net: a dual-channel U-shaped network for image splicing forgery detection
  • Hongwei Ding, Leiyang Chen, Q. Tao, Zhongwang Fu, Liang Dong, Xiaohui Cui
  • Medicine
  • Neural computing & applications
  • 2021
TLDR
A new image tamper location method based on dual-channel U- net, that is, DCU-Net, that has good robustness and can resist noise and JPEG recompression attacks and can accurately locate tampered areas. Expand

References

SHOWING 1-10 OF 21 REFERENCES
Exploiting Spatial Structure for Localizing Manipulated Image Regions
TLDR
A high confidence detection framework which can localize manipulated regions in an image by learning the boundary discrepancy between manipulated and non-manipulated regions with the combination of LSTM and convolution layers. Expand
Learning Rich Features for Image Manipulation Detection
TLDR
A two-stream Faster R-CNN network is proposed and trained end-to-end to detect the tampered regions given a manipulated image and fuse features from the two streams through a bilinear pooling layer to further incorporate spatial co-occurrence of these two modalities. Expand
Constrained Convolutional Neural Networks: A New Approach Towards General Purpose Image Manipulation Detection
TLDR
This paper has developed a new type of CNN layer, called a constrained convolutional layer, that is able to jointly suppress an image’s content and adaptively learn manipulation detection features. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries
TLDR
A high-confidence manipulation localization architecture that utilizes resampling features, long short-term memory (LSTM) cells, and an encoder–decoder network to segment out manipulated regions from non-manipulated ones is proposed. Expand
ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features
TLDR
The forgery localization problem is formulated as a local anomaly detection problem, a Z-score feature is designed to capture local anomaly, and a novel long short-term memory solution is proposed to assess local anomalies. Expand
Mask R-CNN
TLDR
This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. Expand
CBAM: Convolutional Block Attention Module
TLDR
The proposed Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks, can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. Expand
Fighting Fake News: Image Splice Detection via Learned Self-Consistency
TLDR
A learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs to determine whether an image is self-consistent — that is, whether its content could have been produced by a single imaging pipeline. Expand
Image Splicing Localization using a Multi-task Fully Convolutional Network (MFCN)
TLDR
Experiments show that the SFCN and MFCN outperform existing splicing localization algorithms, and that the M FCN can achieve finer localization than the S FCN. Expand
...
1
2
3
...