DINOv3 with LoRA adaptation and a lightweight convolutional decoder achieves higher average pixel-level F1 scores than previous state-of-the-art specialized methods for image manipulation localization on multiple benchmarks.
Mesoscopic insights: Orchestrating multi- scale & hybrid architecture for image manipulation localiza- tion, 2024
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
-
DINOv3 Beats Specialized Detectors: A Simple Foundation Model Baseline for Image Forensics
DINOv3 with LoRA adaptation and a lightweight convolutional decoder achieves higher average pixel-level F1 scores than previous state-of-the-art specialized methods for image manipulation localization on multiple benchmarks.