SIGMA generates accurate IML masks via semantic feature differencing and instruction-guided cross-modal refinement, yielding a 1.1M training set that boosts six detectors by 18.34% F1 on five datasets.
Deal-300k: Diffusion- based editing area localization with a 300k-scale dataset and frequency-prompted baseline
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
SIGMA generates accurate IML masks via semantic feature differencing and instruction-guided cross-modal refinement, yielding a 1.1M training set that boosts six detectors by 18.34% F1 on five datasets.