Research map / Graph learning / Knowledge and temporal graphs
Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation
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 the general-knowledge graph to the report-generation base model (ablation) | DCL · IU-Xray | CIDEr: 0.383 -> 0.535 | Helped |
| add retrieved specific knowledge K_I to the general-knowledge graph (ablation) | DCL · IU-Xray | CIDEr: 0.535 -> 0.557 | Helped |
| add IRC loss (ablation) | DCL with graph and retrieved knowledge · IU-Xray | CIDEr: 0.557 -> 0.580 | Helped |
| add IRM loss alongside IRC (ablation) | DCL with graph, retrieved knowledge, and IRC · IU-Xray | CIDEr: 0.580 -> 0.586 | Helped |
| add IRC rather than IRM as the contrastive objective (ablation) | DCL with graph and retrieved knowledge · IU-Xray | CIDEr: 0.564 -> 0.580 | Helped |
| use pretrained SciBert initialization (ablation) | DCL · IU-Xray | CIDEr: 0.580 -> 0.586 | Helped |
| use pretrained ViT initialization (ablation) | DCL · IU-Xray | CIDEr: 0.527 -> 0.586 | Helped |
| add the dynamic graph (ablation) | DCL · MIMIC-CXR | F1-score: 0.194 -> 0.373 | Helped |
| add IRC loss (ablation) | DCL · MIMIC-CXR | F1-score: 0.359 -> 0.373 | Helped |
| add IRM loss (ablation) | DCL · MIMIC-CXR | F1-score: 0.372 -> 0.373 | Helped |
Closest papers by meaning
- Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation (CVPR 2025 · similarity 0.91)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.88)
- Instance-level Expert Knowledge and Aggregate Discriminative Attention for Radiology Report Generation (CVPR 2024 · similarity 0.87)
- Bootstrapping Large Language Models for Radiology Report Generation (AAAI 2024 · similarity 0.86)
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.85)
- DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching (AAAI 2025 · similarity 0.85)
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.