Research map / Label-efficient and robust learning / Recognition and long-tail
Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
Read the paperCheck 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 |
|---|---|---|---|
| Add MODL and KNNS to the single target model | DenseNet-121 (B) · NIH Chest X-ray | Mean AUC: increased by 3.22% | Helped |
| Add MODL and KNNS to the single target model | DenseNet-121 (B) · CheXpert | Mean AUC: increases the mean AUC by 3.26% | Helped |
| Add MODL without KNNS (ablation) | DenseNet-121 (B) · NIH Chest X-ray | Mean AUC: increased by 2.22% | Helped |
| Add MODL without KNNS (ablation) | DenseNet-121 (B) · CheXpert | Mean AUC: increased by 1.98% | Helped |
| Add KNNS without MODL (ablation) | DenseNet-121 (B) · NIH Chest X-ray | Mean AUC: increased by 2.42% | Helped |
| Add KNNS without MODL (ablation) | DenseNet-121 (B) · CheXpert | Mean AUC: increased by 2.11% | Helped |
| Add KNNS with K set to 3 (ablation) | DenseNet-121 (B) · CheXpert | Mean AUC improvement: 1.14% | Helped |
| Set KNNS K to 5 (ablation) | DenseNet-121 (B) · CheXpert | Mean AUC improvement: 1.68% | Helped |
| Set KNNS K to 7 (ablation) | DenseNet-121 (B) · CheXpert | Mean AUC improvement: 1.98% | Helped |
| Increase K beyond 7 (ablation) | KNNS · CheXpert | Mean AUC improvement | Mixed |
| Use MODL and KNNS together instead of either component alone (ablation) | DenseNet-121 (B) · NIH Chest X-ray and CheXpert | Mean AUC | Helped |
| Use the proposed single target model rather than Model Ensemble 1 | CheXpert · CheXpert | Mean AUC: outperforms Model Ensemble 1 by 0.44% | Helped |
Closest papers by meaning
- Learning Low-Rank Feature for Thorax Disease Classification (NeurIPS 2024 · similarity 0.88)
- Novel Class Discovery in Chest X-rays via Paired Images and Text (AAAI 2024 · similarity 0.87)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.86)
- A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis (NeurIPS 2024 · similarity 0.84)
- BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays (NeurIPS 2024 · similarity 0.84)
- Combining Graph Transformers Based Multi-Label Active Learning and Informative Data Augmentation for Chest Xray Classification (AAAI 2024 · similarity 0.83)
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.