AI Paper Atlas

Research map / Detection and segmentation / CNN features

DetailSemNet: Elevating Signature Verification through Detail-Semantic Integration

Meng-Cheng Shih, Tsai-Ling Huang, Yu-Heng Shih, Hong-Han Shuai, Hsuan-Tung Liu, Yi-Ren Yeh, Ching-Chun Huang

ECCV 2024 · Detection and segmentation › CNN features · approach: Forgery detection · 7 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 SemanticsAttend branch (ablation)DetailSemNet · BHSig-HEER (%): 21.06 -> 2.07Improved
add SemanticsAttend branch (ablation)DetailSemNet · ChiSigEER (%): 29.01 -> 5.85Improved
increase number of reference signatures from 1 to 3 (ablation)DetailSemNet · GPDS SyntheticEER (%): 11.69 -> 8.06Improved
add cross-entropy classifier on siamese features (ablation)DetailSemNet · GPDS SyntheticEER (%): 11.69 -> 8.92Improved
set fusion weight lambda0 to 1.0 instead of 0.1, 10 or 100 (ablation)DetailSemNet · BHSig-HEER (%): 2.52 / 2.77 / 3.47 -> 2.07Improved
fine-tune only Conv_fuse on target dataset instead of zero-shot (ablation)DetailSemNet · BHSig-B (trained on BHSig-H)EER (%): 7.46 -> 4.70Improved
use ResNet50 CNN backbone instead of ViT (ablation)DetailSemNet · ChiSigAccuracy (%): 87.79 -> 87.28Hurt

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