COMICS: End-to-End Bi-Grained Contrastive Learning for Multi-Face Forgery Detection
文献类型：期刊论文
| 作者 | Zhang, Cong1; Qi, Honggang1; Wang, Shuhui2; Li, Yuezun4; Lyu, Siwei5 |
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2024-10-01 |
| 卷号 | 34期号:10页码:10223-10236 |
| 关键词 | Face recognition Forgery Feature extraction Proposals Object detection Faces Generators DeepFake multi-face forgery detection contrastive learning fine-grained feature learning |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2024.3405563 |
| 英文摘要 | DeepFakes have raised serious societal concerns, leading to a great surge in detection-based forensics methods in recent years. Face forgery recognition is a standard detection method that usually follows a two-phase pipeline, i.e., it extracts the face first and then determines its authenticity by classification. While those methods perform well in ideal experimental environment, they face challenges when dealing with DeepFakes in the wild involving complex background and multiple faces of varying sizes. Moreover, most face forgery recognition methods can only process one face at a time. One straightforward way to address this issue is to simultaneous process multi-face by integrating face extraction and forgery detection in an end-to-end fashion by adapting advanced object detection architectures. However, as these object detection architectures are designed to capture the discriminative features of different object categories rather than the subtle forgery traces among the faces, the direct adaptation suffers from limited representation ability. In this paper, we propose Contrastive Multi-FaceForensics (COMICS), an end-to-end framework for multi-face forgery detection. COMICS integrates face extraction and forgery detection in a seamless manner and adapts to the advanced object detection architectures. The core of the proposed framework is a bi-grained contrastive learning approach that explores face forgery traces at both the coarse- and fine-grained levels. Specifically, coarse-grained level contrastive learning captures the discriminative features among positive and negative proposal pairs at multiple layers produced by the proposal generator, and the fine-grained level contrastive learning captures the pixel-wise discrepancy between the forged and original areas of the same face and the pixel-wise content inconsistency among different faces. Extensive experiments on the OpenForensics and FFIW datasets demonstrate that our method outperforms other counterparts and shows great potential for being integrated into various architectures. Codes are available at https://github.com/zhangconghhh/COMICS. |
| 资助项目 | China Postdoctoral Science Foundation[2021TQ0314] ; China Postdoctoral Science Foundation[2021M703036] ; National Key Research and Development Program of China[2023YFC2508704] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[62271466] |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001346503100062 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/39489]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Li, Yuezun |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Peng Cheng Lab, Shenzhen 518066, Peoples R China 4.Ocean Univ China, Coll Comp Sci & Technol, Qingdao 266005, Peoples R China 5.Univ Buffalo State Univ New York Buffalo, Dept Comp Sci & Engn, Amherst, NY 14068 USA |
| 推荐引用方式 GB/T 7714 | Zhang, Cong,Qi, Honggang,Wang, Shuhui,et al. COMICS: End-to-End Bi-Grained Contrastive Learning for Multi-Face Forgery Detection[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,34(10):10223-10236. |
| APA | Zhang, Cong,Qi, Honggang,Wang, Shuhui,Li, Yuezun,&Lyu, Siwei.(2024).COMICS: End-to-End Bi-Grained Contrastive Learning for Multi-Face Forgery Detection.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,34(10),10223-10236. |
| MLA | Zhang, Cong,et al."COMICS: End-to-End Bi-Grained Contrastive Learning for Multi-Face Forgery Detection".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34.10(2024):10223-10236. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。