AI Paper Atlas

Research map / Detection and segmentation / CNN features

Enhancing Tampered Text Detection through Frequency Feature Fusion and Decomposition

Zhongxi Chen, Shen Chen, Taiping Yao, Ke Sun, Shouhong Ding, Xianming Lin, Liujuan Cao, Rongrong Ji

ECCV 2024 · Detection and segmentation › CNN features · approach: Forgery detection · 16 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 DCT Frequency Perception Head to the RGB segmenter (ablation)ConvNextV2-Uper · DocTamper-FCDIoU: 0.80 -> 0.83Improved
add the Visual Enhancement Module with zero-initialized conv fusion on top of FPH (ablation)FFDN · DocTamper-TIoU: 0.86 -> 0.88Improved
combine VEM and WFE together on top of FPH (ablation)FFDN · DocTamper-TIoU: 0.88 -> 0.90Improved
zero-initialized conv for frequency features instead of random init (ablation)VEM · DocTamper-TIoU: 0.882 -> 0.895Improved
use addition instead of max for fusing frequency and RGB features (ablation)VEM · DocTamper-TIoU: 0.881 -> 0.895Improved
use proposed CA+SA enhancement instead of CBAM (ablation)VEM · DocTamper-TIoU: 0.877 -> 0.895Improved
add attention enhancement to wavelet components (learnable) instead of fixed DWT (ablation)WFE · DocTamper-TIoU: 0.867 -> 0.895Improved
add high-frequency enhancement in FFM (vs low-frequency only) (ablation)WFE · DocTamper-TIoU: 0.874 -> 0.895Improved
add low-frequency enhancement in FFM on top of high-frequency (ablation)WFE · DocTamper-TIoU: 0.892 -> 0.895Improved
apply the FFDN modules to a Swin-S backbone (ablation)Swin-Uper · DocTamper-TF1: 0.73 -> 0.82Improved
use FFDN instead of DTD under JPEG Q75 compressionDocTamper-T · DocTamper-T, Q75IoU: 0.75 -> 0.82Improved
FFDN versus RGB-only ConvNextV2 on average drop at Q75DocTamper-T · DocTamper-T, Q75avg drop from Q100 (%): 17.8% -> 20.2%Hurt

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