Research map / Vision-language and multimodal / Cross-modal learning
Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation
Qin Zhou, Guoyan Liang, Xindi Li, Jingyuan Chen, Zhe Wang, Chang Yao, Sai Wu
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 |
|---|---|---|---|
| add Learnable Retrieval Enhancer (LRE) to baseline (ablation) | REVTAF · MIMIC-CXR | Avg: 0.369 -> 0.384 | Improved |
| add FVTAF module to baseline (ablation) | REVTAF · MIMIC-CXR | Avg: 0.369 -> 0.383 | Improved |
| add both LRE and FVTAF to baseline (ablation) | REVTAF · MIMIC-CXR | Avg: 0.369 -> 0.397 | Improved |
| add FVTAF on top of LRE (ablation) | REVTAF · MIMIC-CXR | Avg: 0.384 -> 0.397 | Improved |
| add LRE on top of FVTAF (ablation) | REVTAF · MIMIC-CXR | Avg: 0.383 -> 0.397 | Improved |
| add LRE and FVTAF (ablation) | REVTAF · MIMIC-CXR | BLEU-4: 0.159 -> 0.182 | Improved |
| add LRE and FVTAF (ablation) | REVTAF · MIMIC-CXR | CE F1: 0.562 -> 0.592 | Improved |
| use REVTAF instead of EKAGen | REVTAF · MIMIC-CXR | Avg: 0.323 -> 0.397 | Improved |
| use REVTAF instead of PromptMRG | REVTAF · IU X-Ray | Avg: 0.222 -> 0.251 | Improved |
| use REVTAF instead of GPT-4 | REVTAF · MIMIC-CXR (16 samples) | Avg: 0.192 -> 0.347 | Improved |
| use REVTAF instead of GPT-4.5 for inference time | REVTAF · MIMIC-CXR (16 samples) | inference time (s): 18.72 -> 3.36 | 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.
- PromptMRG — PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation (AAAI 2024) · better on 5 of 5 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
- DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation (CVPR 2025 · similarity 0.90)
- Automatic Radiology Reports Generation via Memory Alignment Network (AAAI 2024 · similarity 0.90)
- S2D-Align: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation (AAAI 2026 · similarity 0.88)
- Bootstrapping Large Language Models for Radiology Report Generation (AAAI 2024 · similarity 0.87)
- AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval (CVPR 2024 · similarity 0.87)
- LLM-RG4: Flexible and Factual Radiology Report Generation Across Diverse Input Contexts (AAAI 2025 · similarity 0.86)
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.
