Research map / Label-efficient and robust learning / Semi-supervised learning
ACPL: Anti-Curriculum Pseudo-Labelling for Semi-Supervised Medical Image Classification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ACPL instead of the strongest listed SSL baseline | Chest X-Ray14 · Chest X-Ray14 test, 20% labelled | mean AUC: 81.06 -> 81.77 | Helped |
| Use ACPL instead of the strongest listed SSL baseline | ISIC2018 · ISIC2018 test, 20% labelled | AUC: 93.58 -> 94.36 | Helped |
| Select high-information rather than low-information unlabelled samples (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 67.76 ± 1.05 -> 74.44 ± 0.38 | Helped |
| Add ASP to high-information selection (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 73.81 ± 0.75 -> 74.44 ± 0.38 | Helped |
| Add ASP to medium-information selection (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 70.83 ± 1.49 -> 71.16 ± 0.51 | Helped |
| Add ASP to low-information selection (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 67.18 ± 2.40 -> 67.76 ± 1.05 | Helped |
| Use informative mixup instead of model-only pseudo-labels (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 72.63 -> 74.44 | Helped |
| Use informative mixup instead of KNN-only pseudo-labels (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 72.45 -> 74.44 | Helped |
| Weight model and KNN predictions by sample density rather than random α (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 73.23 -> 74.44 | Helped |
| Use informative mixup instead of regular MixUp (ablation) | ACPL · Chest X-Ray14 test, 2% labelled | AUC: 69.28 -> 74.44 | Helped |
Closest papers by meaning
- Towards Realistic Semi-supervised Medical Image Classification (AAAI 2025 · similarity 0.88)
- Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification (CVPR 2024 · similarity 0.86)
- BoostMIS: Boosting Medical Image Semi-Supervised Learning With Adaptive Pseudo Labeling and Informative Active Annotation (CVPR 2022 · similarity 0.86)
- Novel Class Discovery in Chest X-rays via Paired Images and Text (AAAI 2024 · similarity 0.86)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.85)
- Semi-supervised TEE Segmentation via Interacting with SAM Equipped with Noise-Resilient Prompting (AAAI 2024 · similarity 0.84)
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.