AI Paper Atlas

Research map / Image generation / Editing and style transfer

Detective SAM: Adaptive AI-Image Forgery Localization

Gert Lek, Nicolas van Schaik, Chaoyi Zhu, Pin-Yu Chen, Robert Birke, Lydia Y. Chen

ICLR 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 0 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
add Gaussian blur and noise perturbation clues versus none (ablation)Detective SAM · SIDA+MagicBrush validationIoU: 36.22 -> 50.52Improved
add JPEG to Noise + Blur perturbations (ablation)Detective SAM · SIDA+MagicBrush validationIoU: 50.52 -> 52.58Improved
add Gaussian noise to Gaussian blur (ablation)Detective SAM · SIDA+MagicBrush validationIoU: 48.17 -> 50.52Improved
use transformer, uncertainty and spatial-gating mask adapter instead of simple convolution (ablation)Detective SAM · SIDA+MagicBrush validationIoU: 44.48 -> 50.52Improved
add feature adapters (ablation)Detective SAM · SIDA+MagicBrush validationIoU: 14.29 -> 50.52Improved
use SAM2 mask decoder instead of heatmap directly (ablation)Detective SAM · SIDA+MagicBrush validationIoU: 36.41 -> 50.52Improved
fine-tune on 500 FLUX-Bench and QWEN-Bench samplesDetective SAM · FLUX-BenchIoU: 18.70 -> 43.08Improved
fine-tune on 500 FLUX-Bench and QWEN-Bench samplesDetective SAM · Avg OOD IoUIoU: 34.68 -> 35.57Improved
fine-tune on 500 FLUX-Bench and QWEN-Bench samplesDetective SAM · NanoBananaIoU: 19.34 -> 27.00Improved
add 20% replay during fine-tuning (ablation)Detective SAM fine-tuning · ID and OOD IoUIoUImproved
fine-tune sequentially FLUX then QWEN versus FLUX onlyDetective SAM · Avg OOD IoUIoU: 35.90 -> 37.68Improved
overrepresent QWEN (1500) vs balanced fine-tuningDetective SAM · QWEN-Bench / FLUX-BenchIoU: 41.44 -> 44.94 (QWEN); 43.08 -> 42.16 (FLUX)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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