AI Paper Atlas

Research map / Detection and segmentation / CNN features

Attention Based Glaucoma Detection: A Large-Scale Database and CNN Model

Liu Li, Mai Xu, Xiaofei Wang, Lai Jiang, Hanruo Liu

CVPR 2019 · Detection and segmentation › CNN features · approach: Convolution-transformer backbones · 279 citations (OpenAlex)

Check 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 the attention prediction subnet (APS) (ablation)AG-CNN without APS or PAL · LAG testAccuracy: 90.8% -> 94.0%Improved
Add pathological area localization (PAL) alongside APS (ablation)AG-CNN without APS or PAL · LAG testAccuracy: 90.8% -> 95.3%Improved
Add APS when PAL is present (ablation)AG-CNN without APS · LAG testAccuracy: 87.1% -> 95.3%Improved
Add PAL when APS is present (ablation)AG-CNN without PAL · LAG testAccuracy: 94.0% -> 95.3%Improved
Use the multi-scale block instead of the conventional residual shortcut connection (ablation)AG-CNN · LAG testAccuracy: 92.2% -> 95.3%Improved
Use AG-CNN rather than the strongest compared baselineGlaucoma detection · LAG testAccuracy: 89.7% -> 95.3%Improved
Use AG-CNN rather than the strongest compared baselineGlaucoma detection · RIM-ONESensitivity: 71.7% -> 84.8%Improved

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