AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

BioFors: A Large Biomedical Image Forensics Dataset

Ekraam Sabir, Soumyaroop Nandi, Wael Abd-Almageed, Prem Natarajan

ICCV 2021 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use dense feature matching (DenseField ZM) instead of sparse keypoints (SIFT)external duplication detection · BioFors EDD combinedMCC image-level: 0.142 -> 0.278Improved
use dense matching (DF-PCT) instead of block-based DCTinternal duplication detection · BioFors IDD combinedMCC image-level: 0.196 -> 0.569Improved
use DF-PCT instead of deep BusterNetinternal duplication detection · BioFors IDD combinedMCC pixel-level: 0.107 -> 0.364Improved
use deep DMVN instead of DF-ZMexternal duplication detection · BioFors EDD Blot/GelMCC pixel-level: 0.192 -> 0.430Mixed
use fine-tuned ManTraNet instead of a simple CNN baselinecut/sharp-transition detection · BioFors CSTDimage-level F1: 0.212 -> 0.253Improved
use ManTraNet instead of CNN baselinecut/sharp-transition detection · BioFors CSTDimage-level MCC: 0.098 -> 0.170Improved
use DenseNet instead of VGG16 for image-class classificationBioFors image classification · BioFors testaccuracy: 97.11% -> 97.67%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy