Improving the Generalization and Robustness of Computer‐Generated Image Detection Based on Contrastive Learning

Authors:
Open Access
Publisher website
Google Scholar
Abstract
With the rapid development of image generation techniques, it becomes much more difficult to distinguish high‐quality computer‐generated (CG) images from photographic (PG) images, challenging the authenticity and credibility of digital images. Therefore, distinguishing CG images from PG images has become an important research problem in image forensics, and it is crucial to develop reliable methods to detect CG images in practical scenarios. In this paper, we proposed a forensics contrastive learning (FCL) framework to adaptively learn intrinsic forensics features for the general and robust detection of CG images. The data augmentation module is specially designed for CG image forensics, which reduces the interference of forensic‐irrelevant information and enhances discrimination features between CG and PG images in both the spatial and frequency domains. Instance‐wise contrastive loss and patch‐wise contrastive loss are simultaneously applied to capture critical discrepancies between CG and PG images from global and local views. Extensive experiments on different public datasets and common postprocessing operations demonstrate that our approach can achieve significantly better generalization and robustness than the state‐of‐the‐art approaches. This manuscript was submitted as a pre‐print in the following link https://papers.ssrn.com/-sol3/papers.cfm?abstract_id=4778441 .
Funding Information
  • National Natural Science Foundation of China (62102100)
  • National Natural Science Foundation of China (62102462)
  • Basic and Applied Basic Research Foundation of Guangdong Province (2022A1515010108)
  • Guangdong Province Key Laboratory of Information Security Technology (2023B1212060026)
  • Guangdong Polytechnic Normal University (2021SDKYA127)
  • Guangdong Polytechnic Normal University (2022SDKYA027)

This publication has 39 references indexed in Scilit: