Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly-Supervised Metric Learning With Cross-Module Communications for the Classification of Anterior Chamber Angle Images
Jingqi Huang, Yue Ning, Dong Nie, Linan Guan, Xiping Jia
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use GCNet with weakly supervised structure learning and cross-module communication instead of UPS | Glaucoma image classification · ACA test set | ACC: 76.75±1.55 -> 79.19±0.72 | Improved |
| Use GCNet with weakly supervised structure learning and cross-module communication instead of UPS | Glaucoma image classification · ACA test set | AUC: 93.74±0.68 -> 94.32±0.42 | Improved |
| Use GCNet with weakly supervised structure learning and cross-module communication instead of UPS | Glaucoma image classification · ACA test set | F1: 75.70±1.56 -> 78.53±0.29 | Improved |
| Use GCNet with weakly supervised structure learning and cross-module communication instead of ResNet | Glaucoma image classification · REFUGE test set | ACC: 95.25±0.57 -> 96.30±0.43 | Improved |
| Use GCNet with weakly supervised structure learning and cross-module communication instead of UPS | Glaucoma image classification · REFUGE test set | AUC: 94.60±0.72 -> 97.20±0.326 | Improved |
| Use GCNet with weakly supervised structure learning and cross-module communication instead of ResNet | Glaucoma image classification · REFUGE test set | F1: 97.37±0.32 -> 97.97±0.23 | Improved |
| Add cross-module communication (ablation) | GCNet-C · ACA test set | ACC: 76.95±0.76 -> 79.19±0.72 | Improved |
| Add cross-module communication (ablation) | GCNet-C · REFUGE test set | AUC: 96.70±0.53 -> 97.20±0.33 | Improved |
| Add embedding module (ablation) | GCNet-CE · ACA test set | ACC: 76.39±0.26 -> 79.19±0.72 | Improved |
| Add embedding module (ablation) | GCNet-CE · REFUGE test set | AUC: 95.60±0.42 -> 97.20±0.33 | Improved |
| Add pseudo-labeling (ablation) | GCNet-CEP · ACA test set | ACC: 75.97±0.24 -> 79.19±0.72 | Improved |
| Add pseudo-labeling (ablation) | GCNet-CEP · REFUGE test set | AUC: 94.78±0.22 -> 97.20±0.33 | Improved |
Closest papers by meaning
- Weakly-Supervised Simultaneous Evidence Identification and Segmentation for Automated Glaucoma Diagnosis (AAAI 2019 · similarity 0.87)
- FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs (NeurIPS 2026 · similarity 0.82)
- SuperJunction: Learning-Based Junction Detection for Retinal Image Registration (AAAI 2024 · similarity 0.80)
- Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning (NeurIPS 2024 · similarity 0.80)
- Show and Segment: Universal Medical Image Segmentation via In-Context Learning (CVPR 2025 · similarity 0.79)
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (NeurIPS 2024 · similarity 0.79)
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.
