用Mamba结构实现轻量高效图像篡改定位，精度超群且计算少
A Lightweight and Effective Image Tampering Localization Network with Vision Mamba
- 基于视觉Mamba构建多尺度全局特征提取，线性复杂度建模长程依赖
- 轻量解码器结合无参上采样与噪声增强策略，提升伪造痕迹敏感度
- 10个标准数据集验证，性能领先且计算开销最低，适合实际部署
当前图像篡改定位方法主要依赖卷积神经网络（CNN）和Transformer。CNN局部感受野有限，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，我们提出一种基于视觉Mamba的轻量高效取证网络ForMa，用于盲图像篡改定位。ForMa通过线性复杂度捕获多尺度全局特征，实现高效的全局依赖建模；再通过轻量解码器生成像素级定位图，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，融合篡改图像中的互补伪造痕迹，增强解码器对伪造线索的敏感性。在10个标准数据集上的实验表明，ForMa在泛化能力和鲁棒性方面达到当前最优水平，同时保持最低的计算复杂度。代码已公开于https://github.com/multimediaFor/ForMa。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。