InfoPrint uses variational information bottleneck regularization to learn camera-model noise residuals, achieving improved splice localization on DSO-1, NC16, and NC17 benchmarks and qualitative detection of GAN inpainting.
Alemi, Ian Fischer, Joshua V
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics
InfoPrint uses variational information bottleneck regularization to learn camera-model noise residuals, achieving improved splice localization on DSO-1, NC16, and NC17 benchmarks and qualitative detection of GAN inpainting.