Operation-wise Attention Network for Tampering Localization Fusion

TL;DR

This paper introduces an attention-based deep learning fusion framework that combines multiple image tampering localization methods to produce a more accurate and interpretable tampering map without requiring expert knowledge.

Contribution

It proposes a novel deep learning fusion model with an attention mechanism that effectively combines multiple forensics algorithms for improved tampering localization.

Findings

Outperforms individual forensics techniques in most cases

Achieves competitive results on three public datasets

Provides an interpretable fused tampering localization map

Abstract

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.