针对高分辨率扩散伪造检测，提出轻量级高效定位模型。
EfficientIML: Efficient High-Resolution Image Manipulation Localization
- 用三阶段轻量级EfficientRWKV捕捉全局与局部特征
- 在1200+张高分辨率扩散伪造图上实现更优定位精度与速度
- 适合实时图像取证场景，兼顾性能与计算效率
随着成像设备分辨率不断提升及基于扩散模型的伪造方法兴起，现有仅在传统数据集（拼接、复制移动、物体移除）上训练的检测器缺乏对新型伪造类型的识别能力。为此，我们构建了一个包含1200+张扩散生成伪造图像的高分辨率SIF数据集，并提供语义提取掩码。然而，这给现有方法带来计算资源瓶颈，因其计算复杂度过高。为此，我们提出EfficientIML模型，采用轻量级三阶段EfficientRWKV主干网络，该网络融合状态空间与注意力机制，可并行捕获全局上下文与局部细节；同时引入多尺度监督策略，确保分层预测的一致性。在自建数据集与标准基准上的大量实验表明，该方法在定位性能、FLOPs与推理速度上均优于基于ViT及其他SOTA轻量级基线，验证了其在实时图像取证中的适用性。
原文摘要 · Abstract (English)
With imaging devices delivering ever-higher resolutions and the emerging diffusion-based forgery methods, current detectors trained only on traditional datasets (with splicing, copy-moving and object removal forgeries) lack exposure to this new manipulation type. To address this, we propose a novel high-resolution SIF dataset of 1200+ diffusion-generated manipulations with semantically extracted masks. However, this also imposes a challenge on existing methods, as they face significant computational resource constraints due to their prohibitive computational complexities. Therefore, we propose a novel EfficientIML model with a lightweight, three-stage EfficientRWKV backbone. EfficientRWKV's hybrid state-space and attention network captures global context and local details in parallel, while a multi-scale supervision strategy enforces consistency across hierarchical predictions. Extensive evaluations on our dataset and standard benchmarks demonstrate that our approach outperforms ViT-based and other SOTA lightweight baselines in localization performance, FLOPs and inference speed, underscoring its suitability for real-time forensic applications.
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。