Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metrics
Matt Y. Cheung, Ashok Veeraraghavan, Guha Balakrishnan
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 |
|---|---|---|---|
| calibrate in feature space (COMPASS-J) instead of output-space SCP | conformal prediction for segmentation area · Skin Lesion (alpha=0.10) | interval size: 1813±127 -> 1179±53 | Improved |
| calibrate in feature space (COMPASS-J) instead of output-space SCP | conformal prediction for segmentation area · PolyP (alpha=0.10) | interval size: 6237±564 -> 4056±293 | Improved |
| use deeper features (COMPASS-J) instead of final logits (COMPASS-L) (ablation) | COMPASS · PolyP (alpha=0.05) | interval size: 6376±769 -> 5489±575 | Improved |
| use deeper features (COMPASS-J) instead of final logits (COMPASS-L) (ablation) | COMPASS · H&E (alpha=0.05) | interval size: 4408±432 -> 4637±630 | Hurt |
| use COMPASS instead of end-to-end CQR trained with Tversky loss | segmentation interval · Skin Lesion (alpha=0.10) | interval size: 1351±75 -> 1179±53 | Improved |
| add more principal components to COMPASS-J (ablation) | COMPASS-J · segmentation area | interval tightness | No clear effect |
| sum spatial dimensions of Jacobians before PCA (ablation) | COMPASS-J · explained variance of Jacobians | explained variance | Improved |
| use feature or Jacobian weights from deep layers in weighted CP (COMPASS-J) | weighted COMPASS · H&E and Skin Lesion covariate shift | coverage | Improved |
| use class-label weights for weighted CP | output-space CP · Skin Lesion covariate shift | coverage | Hurt |
| use feature weighting with shallow-layer methods (COMPASS-L, E2E-CQR) | weighted CP · H&E covariate shift | coverage | Hurt |
Closest papers by meaning
- CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition (ICLR 2026 · similarity 0.89)
- Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation (ECCV 2026 · similarity 0.86)
- Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models (CVPR 2026 · similarity 0.86)
- Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation (CVPR 2026 · similarity 0.85)
- Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms (CVPR 2024 · similarity 0.84)
- DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation (CVPR 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.
