Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Kun Guo, Haochen Zhu, Gang Cao• 2023

Related benchmarks

TaskDatasetResultRank
Image Forgery LocalizationColumbia Unseen Domain
mIoU20.9
30
Image Forgery LocalizationCASIA v1
Pixel-level AUC52.9
20
Image Forgery LocalizationCASIA Seen Domain v2
mIoU47.9
15
Image Forgery LocalizationCASIA Unseen Domain v1
mIoU46.5
15
Image Forgery LocalizationDIS25k Unseen Domain
mIoU25.6
15
Image Forgery LocalizationCASIA v2 (test)
DSC54
15
Image Forgery LocalizationIMD Unseen Domain 2020
mIoU19.7
15
Image Forgery LocalizationMSID Unseen Domain
mIoU45.9
15
Image Forgery LocalizationMSID
DSC58.8
15
Image Forgery LocalizationDIS25k
DSC30.8
15
Showing 10 of 17 rows

Other info

Follow for update