Dongping An
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dongping An has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Gaoyuan Dai
School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510642, China
1 shared publication - Kai Chen
China Telecom Stocks Co., Ltd., Beijing 100033, China
1 shared publication - Kai Wang
Beijing Key Lab of Intelligent Telecommunication Software and Multimedia, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Linjie Huang
China Telecom Stocks Co., Ltd., Beijing 100033, China
1 shared publication - Longru Chen
China Telecom Stocks Co., Ltd., Beijing 100033, China
1 shared publication - Zhe Wang
China Telecom Stocks Co., Ltd., Beijing 100033, China
1 shared publication
Latest Publications
- Open Access
- 3 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (19) , 3919
CECL-Net: Contrastive Learning and Edge-Reconstruction-Driven Complementary Learning Network for Image Forgery Localization
While most current image forgery localization (IFL) deep learning models focus primarily on the foreground of tampered images, they often neglect the essential complementary background semantic information. This oversight tends to create significant gaps in these models’ ability to thoroughly interpret and understand a tampered image, thereby limiting their effectiveness in extracting critical tampering traces. Given the above, this paper presents a novel contrastive learning and edge-reconstruction-driven complementary learning network (CECL-Net) for image forgery localization. CECL-Net enhances the understanding of tampered images by employing a complementary learning strategy that leverages foreground and background features, where a unique edge extractor (EE) generates precise edge artifacts, and edge-guided feature reconstruction (EGFR) utilizes the edge artifacts to reconstruct a fully complementary set of foreground and background features. To carry out the complementary learning process more efficiently, we also introduce a pixel-wise contrastive supervision (PCS) method that attracts consistent regions in features while repelling different regions. Moreover, we propose a dense fusion (DF) strategy that utilizes multi-scale and mutual attention mechanisms to extract more discriminative features and improve the representational power of CECL-Net. Experiments conducted on two benchmark datasets, one Artificial Intelligence (AI)-manipulated dataset and two real challenge datasets, indicate that our CECL-Net outperforms seven state-of-the-art models on three evaluation metrics.
- 3 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (19) , 3919
Open AccessCECL-Net: Contrastive Learning and Edge-Reconstruction-Driven Complementary Learning Network for Image Forgery Localization
While most current image forgery localization (IFL) deep learning models focus primarily on the foreground of tampered images, they often neglect the essential complementary background semantic information. This oversight tends to create significant gaps in these models’ ability to thoroughly interpret and understand a tampered image, thereby limiting their effectiveness in extracting critical tampering traces. Given the above, this paper presents a novel contrastive learning and edge-reconstruction-driven complementary learning network (CECL-Net) for image forgery localization. CECL-Net enhances the understanding of tampered images by employing a complementary learning strategy that leverages foreground and background features, where a unique edge extractor (EE) generates precise edge artifacts, and edge-guided feature reconstruction (EGFR) utilizes the edge artifacts to reconstruct a fully complementary set of foreground and background features. To carry out the complementary learning process more efficiently, we also introduce a pixel-wise contrastive supervision (PCS) method that attracts consistent regions in features while repelling different regions. Moreover, we propose a dense fusion (DF) strategy that utilizes multi-scale and mutual attention mechanisms to extract more discriminative features and improve the representational power of CECL-Net. Experiments conducted on two benchmark datasets, one Artificial Intelligence (AI)-manipulated dataset and two real challenge datasets, indicate that our CECL-Net outperforms seven state-of-the-art models on three evaluation metrics.