arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.02306cs.CV
收藏

混合噪声增强的伪造感知预测器用于多人脸篡改检测与定位

Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization

Changtao Miao, Qi Chu, Tao Gong, Zhentao Tan, Zhenchao Jin, Wanyi Zhuang, Man Luo, Honggang Hu, Nenghai Yu

AI总结:

本文提出 MoNFAP 框架,通过 FUP 统一检测与定位任务,并借助混合专家式 MNM 增强噪声与 RGB 特征,同时构建多人脸篡改检测定位基准。

摘要:

随着人脸篡改技术的发展,多人脸场景中的伪造图像正逐渐成为一项更复杂、更逼真的挑战。尽管如此,针对此类多人脸篡改的检测和定位方法仍不完善。传统的篡改定位方法要么通过定位掩码间接获得检测结果,导致检测性能受限;要么采用简单的双分支结构同时获取检测和定位结果,但由于两个任务之间的交互有限,无法有效提升定位能力。本文提出了一个名为 MoNFAP 的新框架,专门面向多人脸篡改检测与定位。MoNFAP 主要引入了两个新颖模块:伪造感知统一预测器(Forgery-aware Unified Predictor,FUP)模块和混合噪声模块(Mixture-of-Noises Module,MNM)。FUP 使用 token 学习策略和多个伪造感知 transformer 整合检测与定位任务,从而促进利用分类信息增强定位能力。此外,受噪声信息在伪造检测中关键作用的启发,MNM 基于混合专家(mixture of experts)理念利用多个噪声提取器来增强通用 RGB 特征,进一步提升本框架的性能。最后,我们建立了一个用于多人脸检测与定位的综合基准,所提出的 MoNFAP 取得了显著性能。代码将公开发布。

英文摘要:

With the advancement of face manipulation technology, forgery images in multi-face scenarios are gradually becoming a more complex and realistic challenge. Despite this, detection and localization methods for such multi-face manipulations remain underdeveloped. Traditional manipulation localization methods either indirectly derive detection results from localization masks, resulting in limited detection performance, or employ a naive two-branch structure to simultaneously obtain detection and localization results, which cannot effectively benefit the localization capability due to limited interaction between two tasks. This paper proposes a new framework, namely MoNFAP, specifically tailored for multi-face manipulation detection and localization. The MoNFAP primarily introduces two novel modules: the Forgery-aware Unified Predictor (FUP) Module and the Mixture-of-Noises Module (MNM). The FUP integrates detection and localization tasks using a token learning strategy and multiple forgery-aware transformers, which facilitates the use of classification information to enhance localization capability. Besides, motivated by the crucial role of noise information in forgery detection, the MNM leverages multiple noise extractors based on the concept of the mixture of experts to enhance the general RGB features, further boosting the performance of our framework. Finally, we establish a comprehensive benchmark for multi-face detection and localization and the proposed \textit{MoNFAP} achieves significant performance. The codes will be made available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑