IMTNet:Improved Multi-Task Copy-Move Forgery Detection Network with Feature Decoupling and Multi-Feature Pyramid  

作　　者：Huan Wang Hong Wang Zhongyuan Jiang Qing Qian Yong Long 

机构地区：[1]School of Information,Guizhou University of Finance and Economics,Guiyang,550025,China [2]College of Big Data Statistics,Guizhou University of Finance and Economics,Guiyang,550025,China

出　　处：《Computers, Materials & Continua》2024年第9期4603-4620,共18页计算机、材料和连续体（英文）

基　　金：supported and founded by the Guizhou Provincial Science and Technology Project under the Grant No.QKH-Basic-ZK[2021]YB311;the Youth Science and Technology Talent Growth Project of Guizhou Provincial Education Department under Grant No.QJH-KY-ZK[2021]132;the Guizhou Provincial Science and Technology Project under the Grant No.QKH-Basic-ZK[2021]YB319;the National Natural Science Foundation of China(NSFC)under Grant 61902085;the Key Laboratory Program of Blockchain and Fintech of Department of Education of Guizhou Province(2023-014).

摘　　要：Copy-Move Forgery Detection(CMFD)is a technique that is designed to identify image tampering and locate suspicious areas.However,the practicality of the CMFD is impeded by the scarcity of datasets,inadequate quality and quantity,and a narrow range of applicable tasks.These limitations significantly restrict the capacity and applicability of CMFD.To overcome the limitations of existing methods,a novel solution called IMTNet is proposed for CMFD by employing a feature decoupling approach.Firstly,this study formulates the objective task and network relationship as an optimization problem using transfer learning.Furthermore,it thoroughly discusses and analyzes the relationship between CMFD and deep network architecture by employing ResNet-50 during the optimization solving phase.Secondly,a quantitative comparison between fine-tuning and feature decoupling is conducted to evaluate the degree of similarity between the image classification and CMFD domains by the enhanced ResNet-50.Finally,suspicious regions are localized using a feature pyramid network with bottom-up path augmentation.Experimental results demonstrate that IMTNet achieves faster convergence,shorter training times,and favorable generalization performance compared to existingmethods.Moreover,it is shown that IMTNet significantly outperforms fine-tuning based approaches in terms of accuracy and F_(1).

关 键 词：Image copy-move detection feature decoupling multi-scale feature pyramids passive forensics 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]