Research map / Label-efficient and robust learning / Recognition and long-tail
DARC: Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray Classification
Zhifang Liao, Junhao Li, HaoKang Ding, Yucheng Song
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 Global Stream (back-door adjustment) (ablation) | ConvNeXt backbone · ChestX-ray14 | mean AUC: 0.828 -> 0.837 | Improved |
| add Local Stream (counterfactual reasoning) (ablation) | ConvNeXt backbone · ChestX-ray14 | mean AUC: 0.828 -> 0.835 | Improved |
| combine both streams (ablation) | DARC · ChestX-ray14 | mean AUC: 0.837 / 0.835 -> 0.857 | Improved |
| add anatomical landmark detection (ablation) | DARC · ChestX-ray14 | mean AUC: 0.846 -> 0.857 | Improved |
| add confounder segmentation (ablation) | DARC · ChestX-ray14 | mean AUC: 0.842 -> 0.857 | Improved |
| use DARC vs CDCL | DARC · ChestX-ray14 | mean AUC: 0.849 -> 0.857 | Improved |
| use DARC vs CDCL | DARC · CheXpert | mean AUC: 0.896 -> 0.907 | Improved |
| use DARC vs CDCL per class | DARC · ChestX-ray14 Hernia | AUC: 0.961 -> 0.924 | Hurt |
| use DARC vs baseline on co-occurring pairs | DARC · ChestX-ray14 co-occurrence pairs | cTPR / cFPR | 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.
- AD-Net — ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment (ICCV 2021) · better on 1 of 1 shared result
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
- Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models (NeurIPS 2026 · similarity 0.88)
- CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays (NeurIPS 2025 · similarity 0.87)
- BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays (NeurIPS 2024 · similarity 0.85)
- AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation (NeurIPS 2025 · similarity 0.85)
- RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability (NeurIPS 2025 · similarity 0.84)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 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.
