Effective Image Tampering Localization via Enhanced Transformer and Co-attention Fusion

TL;DR

This paper introduces EITLNet, a novel image tampering localization network that uses an enhanced transformer and co-attention fusion to improve detection accuracy and robustness against manipulated images.

Contribution

The paper presents a new two-branch transformer-based architecture with attention-based feature fusion for improved image tampering localization.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates high generalization ability and robustness.

Effective fusion of RGB and noise features enhances localization accuracy.

Abstract

Powerful manipulation techniques have made digital image forgeries be easily created and widespread without leaving visual anomalies. The blind localization of tampered regions becomes quite significant for image forensics. In this paper, we propose an effective image tampering localization network (EITLNet) based on a two-branch enhanced transformer encoder with attention-based feature fusion. Specifically, a feature enhancement module is designed to enhance the feature representation ability of the transformer encoder. The features extracted from RGB and noise streams are fused effectively by the coordinate attention-based fusion module at multiple scales. Extensive experimental results verify that the proposed scheme achieves the state-of-the-art generalization ability and robustness in various benchmark datasets. Code will be public at https://github.com/multimediaFor/EITLNet.