SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
SIGMA automatically generates pixel-level masks for image editing localization by fusing semantic feature differencing with instruction grounding. It addresses the lack of large-scale training data by using public editing datasets and a two-stage training process that calibrates noise and disentangles edit noise. The resulting data improves various IML detectors significantly, establishing a model-agnostic supervisory resource.