AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matching

Jiazhen Liu, Xirong Li, Qijie Wei, Jie Xu, Dayong Ding

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 57 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 progressive keypoint expansion (PKE) (ablation)SuperRetina · FIREmAUC: 0.685 -> 0.755Improved
add progressive keypoint expansion (PKE) (ablation)SuperRetina · CLINICALEER (%): 5.14 -> 0.83Improved
add content-based matching to PKE (double matching) (ablation)SuperRetina · FIREmAUC: 0.670 -> 0.755Improved
use hardest plus random negative instead of semi-hard negative sampling (ablation)SuperRetina description loss · FIREmAUC: 0.407 -> 0.755Improved
add descriptor upsampling (ablation)SuperRetina · FIREmAUC: 0.697 -> 0.755Improved
add 2D Gaussian blur (ablation)SuperRetina · FIREmAUC: 0.574 -> 0.755Improved
use Dice loss instead of cross-entropy (ablation)SuperRetina · FIREmAUC: 0.653 -> 0.755Improved
use Dice loss instead of weighted cross-entropy (ablation)SuperRetina · FIREmAUC: 0.704 -> 0.755Improved
use SuperRetina detector instead of SIFT detector (ablation)SuperRetina · FIREmAUC: 0.585 -> 0.755Improved
use SuperRetina descriptor instead of RootSIFT (ablation)SuperRetina · FIREmAUC: 0.705 -> 0.755Improved
use PBO-detected initial keypoints instead of manual labels (ablation)SuperRetina · FIREmAUC: 0.755 -> 0.750No clear effect
finetune on retinal training dataSuperPoint · FIREmAUC: 0.674 -> 0.661Hurt

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