arXiv 2502.099412025-02-14cs.CVcs.CR

基于视觉Mamba的轻量高效图像篡改定位网络

A Lightweight and Effective Image Tampering Localization Network with Vision Mamba

School of Computer and Cyber Sciences, Communication University of China（中国传媒大学计算机与网络空间科学学院）；State Key Laboratory of Media Convergence and Communication, Communication University of China（中国传媒大学媒体融合与传播国家重点实验室）；School of Information Engineering, Changsha Medical University（长沙医学院信息工程学院）

Kun Guo, Gang Cao, Zijie Lou, Xianglin Huang, Jiaoyun Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有图像篡改定位方法的局限，提出基于视觉Mamba的轻量网络ForMa，通过线性复杂度全局特征捕获、轻量解码器及噪声辅助策略，在10个数据集上实现最优泛化鲁棒性且计算复杂度最低。

摘要：

当前图像篡改定位方法主要依赖卷积神经网络（CNNs）和Transformer。CNNs存在局部感受野有限的问题，而Transformer虽能建模全局上下文，但计算复杂度为二次方。近期，状态空间模型Mamba成为具有竞争力的替代方案，可实现线性复杂度的全局依赖建模。受此启发，我们提出基于视觉Mamba的轻量高效取证网络（ForMa），用于盲图像篡改定位。首先，ForMa通过线性复杂度捕获多尺度全局特征，实现高效全局依赖建模；然后，轻量级解码器生成逐像素定位图，该解码器采用无参数像素洗牌层进行上采样；此外，提出噪声辅助解码策略，整合篡改图像的互补操作痕迹，提升解码器对伪造线索的敏感性。在10个标准数据集上的实验结果表明，ForMa在保持最低计算复杂度的同时，实现了最先进的泛化能力和鲁棒性。代码可在https://github.com/multimediaFor/ForMa获取。

英文摘要：

Current image tampering localization methods primarily rely on Convolutional Neural Networks (CNNs) and Transformers. While CNNs suffer from limited local receptive fields, Transformers offer global context modeling at the expense of quadratic computational complexity. Recently, the state space model Mamba has emerged as a competitive alternative, enabling linear-complexity global dependency modeling. Inspired by it, we propose a lightweight and effective FORensic network based on vision MAmba (ForMa) for blind image tampering localization. Firstly, ForMa captures multi-scale global features that achieves efficient global dependency modeling through linear complexity. Then the pixel-wise localization map is generated by a lightweight decoder, which employs a parameter-free pixel shuffle layer for upsampling. Additionally, a noise-assisted decoding strategy is proposed to integrate complementary manipulation traces from tampered images, boosting decoder sensitivity to forgery cues. Experimental results on 10 standard datasets demonstrate that ForMa achieves state-of-the-art generalization ability and robustness, while maintaining the lowest computational complexity. Code is available at https://github.com/multimediaFor/ForMa.

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。