Operation-wise Attention Network for Tampering Localization Fusion
This work addresses the need for easier interpretation of tampering localization results for end users in image forensics, though it is incremental as it adapts an existing architecture for a new task.
The paper tackles the problem of fusing multiple image tampering localization methods to produce a single, interpretable map, and demonstrates that their deep learning-based fusion approach outperforms individual methods and a recent fusion framework in most cases.
In this work, we present a deep learning-based approach for image tampering localization fusion. This approach is designed to combine the outcomes of multiple image forensics algorithms and provides a fused tampering localization map, which requires no expert knowledge and is easier to interpret by end users. Our fusion framework includes a set of five individual tampering localization methods for splicing localization on JPEG images. The proposed deep learning fusion model is an adapted architecture, initially proposed for the image restoration task, that performs multiple operations in parallel, weighted by an attention mechanism to enable the selection of proper operations depending on the input signals. This weighting process can be very beneficial for cases where the input signal is very diverse, as in our case where the output signals of multiple image forensics algorithms are combined. Evaluation in three publicly available forensics datasets demonstrates that the performance of the proposed approach is competitive, outperforming the individual forensics techniques as well as another recently proposed fusion framework in the majority of cases.