AI Paper Atlas

Research map / Detection and segmentation / CNN features

AdaIFL: Adaptive Image Forgery Localization via a Dynamic and Importance-aware Transformer Network

Yuxi Li, Fuyuan Cheng, Wangbo Yu, Guangshuo Wang, Guibo Luo, Yuesheng Zhu

ECCV 2024 · Detection and segmentation › CNN features · approach: Forgery detection · 6 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 feature importance-aware attention (FIA) instead of original attention (ablation)AdaIFL · CASIA v1IoU: .609 -> .661Improved
add adaptive token aggregator (ATA) (ablation)AdaIFL · MISDIoU: .567 -> .606Improved
add dynamic expert groups in the encoder (DyE) (ablation)AdaIFL · CASIA v1IoU: .587 -> .661Improved
add dynamic expert groups in the decoder (DyD) (ablation)AdaIFL · MISDIoU: .591 -> .606Improved
use AdaIFL instead of TruForimage forgery localization · Mean over 5 datasetsIoU: .406 -> .472Improved
heavy Gaussian noise (k=23) applied to test imagesAdaIFL · NIST16 distortionsIoU: .110 vs TruFor .119Hurt
AdaIFL on DSO-1 versus TruForAdaIFL · DSO-1IoU: .237 vs .270Hurt

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