AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Self-Supervised Domain Adaptation for Forgery Localization of JPEG Compressed Images

Yuan Rao, Jiangqun Ni

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 42 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 ICRF-Att attention module (ablation)backbone network · Nim.16, DSO-1, Wild WebMCC/F1Improved
add domain adaptation with JPEG-agent images (DA-Ia) (ablation)backbone with ICRF-Att · Nim.16MCC: 0.351 -> 0.391Improved
add domain adaptation with JPEG-agent images (DA-Ia) (ablation)backbone with ICRF-Att · DSO-1MCC: 0.805 -> 0.822Improved
use JPEG-agent images instead of real JPEG as DA target (ablation)DA strategy · Nim.16, DSO-1, Wild WebMCC: 3.2%, 2.7% and 1.4%Improved
add real JPEG images as DA target (DA-Ic) (ablation)backbone with ICRF-Att · Nim.16MCC: 0.351 -> 0.359Improved
mix JPEG-agent images into training without DA (ablation)backbone with ICRF-Att · Nim.16MCC: 0.351 -> 0.333Hurt
mix JPEG-agent images instead of real JPEG images into training without DA (ablation)backbone with ICRF-Att · Nim.16MCC: 0.256 -> 0.333Improved
mix JPEG-agent images into training without DA (ablation)backbone with ICRF-Att · DSO-1MCC: 0.805 -> 0.774Hurt
use L2 domain loss rather than L1 or MMD (ablation)DA strategy · Nim.16, DSO-1, Wild WebMCC/F1Improved
use alpha = 1 for domain loss weight (ablation)joint loss · IFC training datalocalizationImproved
method vs second best NoiseprintProposed · 7 datasets averageMCC, F1, AP: 5.3%, 5.6% and 8.6%Improved
lower JPEG quality QF=70 to QF=50Proposed · Nim.16F1: 0.317 -> 0.280Hurt

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