Research map / Federated learning and privacy / Personalized and heterogeneous FL
Class-Aware Active Annotation in Federated Semi-Supervised Learning for Medical Image Classification
Meiting Xue, Miaoqi Li, Yukun Shi, Yan Zeng, Jilin Zhang, Jing Ma
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use FSSAL instead of best FSSL baseline | FSSAL · RSNA ICH Dir(0.8) | Acc: 84.56 -> 86.49 | Improved |
| use FSSAL instead of best FSSL baseline | FSSAL · Skin Lesion Dir(0.8) | Recall/F1: F1 57.59 -> 61.91 | Improved |
| use FSSAL with 15% labeled data (ablation) | FSSAL · Skin Lesion | Acc: 94.47 -> 94.08 | No clear effect |
| add all three modules to PMPP only (ablation) | FSSAL · Skin Lesion ablation | F1: 54.80 -> 61.91 | Improved |
| add LAT (class-aware thresholds) alone (ablation) | FSSAL · ablation | F1: 53.96 (ABS only) -> 57.28 (LAT only) | Improved |
| add LAT to PMPP (ablation) | FSSAL · ablation | F1: 54.80 -> 59.53 | Improved |
| add ABS (active sampling) to PMPP+LAT (ablation) | FSSAL · ablation | Acc: 94.10 -> 94.47 | Improved |
| use both private and global models in selector instead of global only (ablation) | FSSAL · Diabetic Dir(0.01) | F1: 46.28 -> 50.40 | Improved |
| use both models instead of private only (ablation) | FSSAL · Diabetic Dir(0.01) | Acc: 86.62 -> 87.00 | Improved |
| vary EMA weight alpha_ema (ablation) | FSSAL · Diabetic | Accuracy | Mixed |
| use private model for pseudo-labels instead of global model (ablation) | FSSAL · Diabetic | pseudo-label accuracy | Improved |
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.
- RSCFed — RSCFed: Random Sampling Consensus Federated Semi-Supervised Learning (CVPR 2022) · better on 2 of 2 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
- Dual-calibrated Co-training Framework for Personalized Federated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.90)
- Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts (CVPR 2024 · similarity 0.88)
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 2024 · similarity 0.88)
- Towards Realistic Semi-supervised Medical Image Classification (AAAI 2025 · similarity 0.87)
- FedCD: Federated Semi-Supervised Learning with Class Awareness Balance via Dual Teachers (AAAI 2024 · similarity 0.87)
- FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (AAAI 2025 · similarity 0.87)
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.
