Research map / Vision-language and multimodal / Cross-modal learning
FAMDR: Feature-Aligned Multimodal Denoising for Reliable Diagnostic Reconciliation in Medical Imaging
Xun Liang, Zhiying Li, Hongxun Jiang
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 CAMAL discrepancy-aware alignment (ablation) | FAMDR · Extended MIMIC-CXR | F1: 0.73 -> 0.83 (-12% without) | Improved |
| add CAMAL discrepancy-aware alignment (ablation) | FAMDR · Extended MIMIC-CXR | IoU: 0.45 -> 0.59 (-24% without) | Improved |
| add CAMAL discrepancy-aware alignment (ablation) | FAMDR · Extended MIMIC-CXR | ECE: 0.11 -> 0.08 (+38% without) | Improved |
| add X-MRA retrieval augmentation (ablation) | FAMDR · Extended MIMIC-CXR | F1: 0.78 -> 0.83 (-6% without) | Improved |
| add X-MRA retrieval augmentation (ablation) | FAMDR · Extended MIMIC-CXR | ECE: 0.10 -> 0.08 (+25% without) | Improved |
| add MCUQ uncertainty quantification (ablation) | FAMDR · Extended MIMIC-CXR | ECE: 0.12 -> 0.08 (+50% without) | Improved |
| add MCUQ uncertainty quantification (ablation) | FAMDR · Extended MIMIC-CXR | F1: 0.80 -> 0.83 (-4% without) | Improved |
| use G-CLAM adaptive residual learning instead of cosine similarity (ablation) | FAMDR · Extended MIMIC-CXR | IoU: 0.49 -> 0.59 (-17% with cosine) | Improved |
| use G-CLAM adaptive residual learning instead of cosine similarity (ablation) | FAMDR · Extended MIMIC-CXR | F1: 0.75 -> 0.83 (-10% with cosine) | Improved |
| set alignment loss weight lambda to 0.5 rather than 0.1 (ablation) | FAMDR · Extended MIMIC-CXR | F1: 0.76 -> 0.83 | Improved |
| raise alignment loss weight lambda from 0.5 to 1.0 (ablation) | FAMDR · Extended MIMIC-CXR | F1: 0.83 -> 0.73 | Hurt |
| raise retrieval weight beta from 1.0 to 2.0 (ablation) | FAMDR · Extended MIMIC-CXR | F1: 0.83 -> 0.77 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PromptMRG — PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation (AAAI 2024) · better on 3 of 3 shared results
- KiUT — KiUT: Knowledge-Injected U-Transformer for Radiology Report Generation (CVPR 2023) · better on 3 of 3 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
- Score-based Self-supervised MRI Denoising (ICLR 2025 · similarity 0.84)
- Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment (NeurIPS 2025 · similarity 0.84)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.83)
- CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification (CVPR 2024 · similarity 0.83)
- A Unified Degradation-Robust Approach to SSL and UDA for 3D Medical Images (AAAI 2025 · similarity 0.83)
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · 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.
