EfficientIML: Efficient High-Resolution Image Manipulation Localization
This addresses the forensic challenge of detecting emerging diffusion-based forgeries in high-resolution images, though it is incremental as it builds on existing localization methods with a new dataset and model.
The paper tackles the problem of detecting diffusion-generated image manipulations in high-resolution images by introducing a new dataset of 1200+ manipulations and proposing EfficientIML, a lightweight model that outperforms SOTA baselines in localization performance, FLOPs, and inference speed.
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.