AI Paper Atlas

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

Geometric Correspondence Constrained Pseudo-Label Alignment for Source-Free Domain Adaptive Fundus Image Segmentation

Zhouhongyuan Hu, Lei Zhang, Lituan Wang, Zhenwei Zhang, Minjuan Zhu, Zhenbin Wang

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-modality medical segmentation adaptation · 0 citations (OpenAlex)

Read the paper

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 pseudo-label alignment alone without SAPE (ablation)GCC · Drishti-GS to RIM-ONE-r3Avg Dice (%): 84.69 -> 84.01Hurt
add Gaussian perturbation to pseudo-label refinement (ablation)Refined pseudo-label · Drishti-GS to RIM-ONE-r3 train setOptic cup Dice (%): 69.29 -> 72.34Improved
add SAPE and filter to alignment (full GCC) (ablation)GCC · Drishti-GS to RIM-ONE-r3Avg Dice (%): 84.01 -> 85.87Improved
add semantic loss Lsem (ablation)geometric correspondence learning · Drishti-GS to RIM-ONE-r3Avg Dice (%): 84.89 -> 85.15Improved
add semantic loss Lsem (ablation)geometric correspondence learning · Drishti-GS to RIM-ONE-r3Avg ASD (pixel): 8.13 -> 7.36Improved
add entropy loss Lent alone (ablation)geometric correspondence learning · Drishti-GS to RIM-ONE-r3Avg Dice (%): 84.89 -> 84.80No clear effect
add entropy loss Lent alone (ablation)geometric correspondence learning · Drishti-GS to RIM-ONE-r3Avg ASD (pixel): 8.13 -> 7.27Improved
combine Lsem and Lent (ablation)geometric correspondence learning · Drishti-GS to RIM-ONE-r3Avg Dice (%): 84.89 -> 85.87Improved
combine Lsem and Lent (ablation)geometric correspondence learning · Drishti-GS to RIM-ONE-r3Avg ASD (pixel): 8.13 -> 6.71Improved
use sample-adaptive perturbation (SAPE) instead of fixed perturbation ratios (ablation)GCC · Drishti-GS to RIM-ONE-r3Avg Dice (%)Improved
vary initial low-Q proportion alpha (ablation)GCC · Drishti-GS to RIM-ONE-r3Avg Dice (%)No clear effect
use GCC instead of CPRGCC · Drishti-GS to RIM-ONE-r3Avg Dice (%): 84.61 -> 85.87Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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