Ivy-Fake delivers a multimodal explainable benchmark for AIGC detection and an RL model that raises GenImage accuracy from 86.88% to 96.32%.
- Penalize if irrelevant aspects are introduced or relevant ones are missing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection
Ivy-Fake delivers a multimodal explainable benchmark for AIGC detection and an RL model that raises GenImage accuracy from 86.88% to 96.32%.