文献类型：期刊文献

英文题名：Combined spatial and frequency dual stream network for face forgery detection

作者：Zhao, Hui[1,2];Li, Xin[1,2];Xu, Bingxin[1,2];Liu, Hongzhe[1,2]

通讯作者：Xu, BX[1];Liu, HZ[1];Xu, BX[2];Liu, HZ[2]

机构：[1]Beijing Union Univ, Dept Robot, Beijing, Peoples R China;[2]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China

第一机构：北京联合大学

通讯机构：[1]corresponding author), Beijing Union Univ, Dept Robot, Beijing, Peoples R China;[2]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China.|[11417103]北京联合大学北京市信息服务工程重点实验室;[11417]北京联合大学;

年份：2024

卷号：10

外文期刊名：PEERJ COMPUTER SCIENCE

收录：;EI(收录号：20241715963792);Scopus(收录号：2-s2.0-85190846144);WOS:【SCI-EXPANDED(收录号:WOS:001203365600001)】；

基金：This work was supported by the National Natural Science Foundation of China (Nos. 62006020, 62171042, 62102033) . The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

语种：英文

外文关键词：Face forgery detection; Multi-scale feature extraction; Cross self attention; Image frequency analysis

摘要：With the development of generative model, the cost of facial manipulation and forgery is becoming lower and lower. Fraudulent data has brought numerous hidden threats in politics, privacy, and cybersecurity. Although many methods of face forgery detection focus on the learning of high frequency forgery traces and achieve promising performance, these methods usually learn features in spatial and frequency independently. In order to combine the information of the two domains, a combined spatial and frequency dual stream network is proposed for face forgery detection. Concretely, a cross self-attention (CSA) module is designed to improve frequency feature interaction and fusion at different scales. Moreover, to augment the semantic and contextual information, frequency guided spatial feature extraction module is proposed to extract and reconstruct the spatial information. These two modules deeply mine the forgery traces via a dual-stream collaborative network. Through comprehensive experiments on different datasets, we demonstrate the effectiveness of proposed method for both within and cross datasets.