Dual Stream Computer-Generated Image Detection Network Based On Channel Joint And Softpool

TL;DR

This paper introduces a dual stream CNN with channel joint and SoftPool for improved detection of computer-generated images, leveraging residual modules and shallow semantic features to outperform existing methods.

Contribution

The paper proposes a novel dual stream CNN architecture with channel joint and SoftPool, enhancing feature extraction for better CG image detection.

Findings

Outperforms existing methods on SPL2018 and DsTok datasets.

Achieves a 3% performance improvement over the state-of-the-art.

Utilizes residual modules and shallow semantic features for effective classification.

Abstract

With the development of computer graphics technology, the images synthesized by computer software become more and more closer to the photographs. While computer graphics technology brings us a grand visual feast in the field of games and movies, it may also be utilized by someone with bad intentions to guide public opinions and cause political crisis or social unrest. Therefore, how to distinguish the computer-generated graphics (CG) from the photographs (PG) has become an important topic in the field of digital image forensics. This paper proposes a dual stream convolutional neural network based on channel joint and softpool. The proposed network architecture includes a residual module for extracting image noise information and a joint channel information extraction module for capturing the shallow semantic information of image. In addition, we also design a residual structure to enhance feature extraction and reduce the loss of information in residual flow. The joint channel information extraction module can obtain the shallow semantic information of the input image which can be used as the information supplement block of the residual module. The whole network uses SoftPool to reduce the information loss of down-sampling for image. Finally, we fuse the two flows to get the classification results. Experiments on SPL2018 and DsTok show that the proposed method outperforms existing methods, especially on the DsTok dataset. For example, the performance of our model surpasses the state-of-the-art by a large margin of 3%.