AI Paper Atlas

Research map / Detection and segmentation / CNN features

SAFL-Net: Semantic-Agnostic Feature Learning Network with Auxiliary Plugins for Image Manipulation Detection

Zhihao Sun, Haoran Jiang, Danding Wang, Xirong Li, Juan Cao

ICCV 2023 · Detection and segmentation › CNN features · approach: Forgery detection · 26 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 dedicated classification head instead of averaging pixel outputs (ablation)SAFL-Net baseline · Coveragepixel-level AUC: 74.1 -> 81.6Improved
add plain boundary prediction auxiliary task (ablation)baseline · IMD20pixel-level AUC: 84.6 -> 79.7Hurt
replace plain boundary task with Boundary Guidance Module differential block (ablation)baseline · IMD20pixel-level AUC: 79.7 -> 87.3Improved
add soft boundary supervision and tailored BGM loss (ablation)BGM · IMD20pixel-level AUC: 87.3 -> 89.9Improved
add semantic suppression image-level constraint (ablation)baseline + BGM · IMD20pixel-level AUC: 89.9 -> 93.1Improved
add patch-level contrastive loss in SSM (ablation)baseline + BGM + SSM#1 · CASIApixel-level AUC: 86.1 -> 90.9Improved
add patch-level contrastive loss in SSM (ablation)baseline + BGM + SSM#1 · Coveragepixel-level AUC: 93.8 -> 93.5No clear effect
SAFL-Net versus PSCC-Net on ColumbiaSAFL-Net · Columbia pretrainedpixel-level AUC: 98.2 vs 96.9Hurt
SAFL-Net versus ObjectFormer on image-level AUCSAFL-Net · CASIA-Dimage-level AUC: 99.70 vs 99.48Hurt

Later papers that compared with this method

1 later accepted paper reports SAFL-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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