GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection

Abstract

Forensic analysis depends on the identification of hidden traces from manipulated images. Traditional neural networks fail in this task because of their inability in handling feature attenuation and reliance on the dominant spatial features. In this work we propose a novel Gated Context Attention Network (GCA-Net) that utilizes the non-local attention block for global context learning. Additionally, we utilize a gated attention mechanism in conjunction with a dense decoder network to direct the flow of relevant features during the decoding phase, allowing for precise localization. The proposed attention framework allows the network to focus on relevant regions by filtering the coarse features. Furthermore, by utilizing multi-scale feature fusion and efficient learning strategies, GCA-Net can better handle the scale variation of manipulated regions. We show that our method outperforms state-of-the-art networks by an average of 4.2% − 5.4% AUC on multiple benchmark datasets. Lastly, we also conduct extensive ablation experiments to demonstrate the method's robustness for image forensics.

Parallel architecture based on transformers and CNNs for renal cell carcinoma image segmentation

“…We train the whole network model end-to-end using the Dice loss function and the binary cross-entropy loss function 𝐿 = 𝐿 𝓌 𝐿 𝓌 , and the combination of both loss functions effectively improve the issue of false positives and overlapping lesion regions [20].…”