MC‐Net: Learning mutually‐complementary features for image manipulation localization. Issue 5 (17th January 2022)

• Record Type: Journal Article
• Authors: Xu, Dengyun; Shen, Xuanjing; Lyu, Yingda; Du, Xiaoyu; Feng, Fuli
• Other Names: Wang Meng guestEditor.; Zhang Chi guestEditor.; Hao Shijie guestEditor.; Yu Jun guestEditor.; Mu Tingting guestEditor.
• Is Part Of: International journal of intelligent systems. Volume 37:Issue 5(2022)
• Page Start: 3072
• Page End: 3089
• Publication Date: 2022-01-17
• Subjects: cross‐feature attentive component -- image manipulation localization -- mutual attentive module -- mutually‐complementary network -- self‐feature attentive component; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; 006.3
• DOI: 10.1002/int.22826
• Languages: English
• ISSNs: 0884-8173

Abstract

Abstract: Deep learning has become an emerging technical for image manipulation localization, which can automatically recognize abnormal traces caused by manipulation. However, as manipulations mainly happens in the foreground regions, these methods largely focus on the foreground contents and neglect the background, which contain complementary signal for fully understanding the image and are meaningful for manipulation localization. We propose a Mutually‐Complementary Network (MC‐Net), which is a two‐branch network to operate the foreground and background features, respectively. To distill complementary signals from the features, we propose a mutual attentive module composed of self‐feature attentive, and cross‐feature attentive components to advance the communication across the foreground and background branches. Extensive qualitative and quantitative experiments demonstrate that our proposed MC‐Net distinctly improves the prediction of foreground and background, obtains consistent performance increments on four benchmark data sets, and significantly outperforms the state‐of‐the‐art methods.