AI Paper Atlas

Research map / Detection and segmentation / CNN features

M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization

Ju-Hyeon Nam, Dong-Hyun Moon, Sang-Chul Lee

ICCV 2025 · Detection and segmentation › CNN features · approach: Forgery detection · 11 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 multi-scale attention to single-spectral M2S block (ablation)M2SFormer · Unseen datasets avg (CASIAv2 training)DSC: 27.1 -> 33.6Improved
add multi-spectral attention to single-scale M2S block (ablation)M2SFormer · Unseen datasets avg (CASIAv2 training)DSC: 27.1 -> 36.1Improved
combine multi-spectral and multi-scale attention (full M2S) (ablation)M2SFormer · Unseen datasets avg (CASIAv2 training)DSC: 36.1 -> 43.0Improved
add multi-scale attention on seen domain (ablation)M2SFormer (single-spectral) · CASIAv2 (seen)DSC: 56.3 -> 55.5Hurt
add difficulty-guided attention with edge-aware calculator (EADC) (ablation)M2SFormer · Unseen datasets avg (CASIAv2 training)DSC: 32.3 -> 43.0Improved
add difficulty-guided attention with edge-aware calculator (EADC) (ablation)M2SFormer · CASIAv2 (seen)DSC: 55.5 -> 58.8Improved
use simple difficulty calculator instead of edge-aware one (ablation)M2SFormer DGA · Unseen datasets avg (CASIAv2 training)DSC: 43.0 -> 30.8Hurt
add simple difficulty calculator + DGA over no DGA (ablation)M2SFormer · Unseen datasets avg (CASIAv2 training)DSC: 32.3 -> 30.8Hurt
PVT-v2-B2 backbone instead of ResNet50 (ablation)M2SFormer · Unseen datasets avg (CASIAv2 training)DSC: 35.6 -> 43.0Improved
PVT-v2-B2 backbone instead of MiT-B2 (ablation)M2SFormer · Unseen datasets avg (CASIAv2 training)DSC: 41.2 -> 43.0Improved
M2SFormer versus PIMNet on CASIAv2 training, DSC on ColumbiaM2SFormer · Columbia, trained on CASIAv2DSC: 32.5 -> 42.4Improved
M2SFormer versus EITLNet on DIS25k training, seen DIS25kM2SFormer · DIS25k (seen), trained on DIS25kDSC: 90.6 -> 87.7Hurt

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