Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation
Referee-Based Quality Estimation flags unreliable polyp segmentations at inference without ground truth, reaching ROC-AUC 0.960 with SegFormer-B0 referees.
RBQE measures agreement between a primary segmentation model and an independently trained referee on a 1,223-image external benchmark drawn from four public datasets. A cross-architecture SegFormer-B0 referee achieves the strongest signal (ROC-AUC 0.960), beating a Test-Time Augmentation baseline by 0.055 ROC-AUC under an identical protocol. Excluding trivially separable empty-mask cases, ROC-AUC falls to 0.876 (SegFormer-B0) and 0.783 (same-architecture control), but RBQE's margin over baselines widens. Progressive rejection of low-agreement predictions increases mean Dice of retained outputs, supporting selective prediction at the cost of one extra forward pass.
- A same-architecture referee differing only in random seed already yields useful reliability signal (ROC-AUC 0.923).
- Rejecting low-agreement cases raises mean Dice of retained predictions, enabling selective prediction.
- A prompt-coupled MedSAM referee underperforms despite maximal architectural diversity.
- Products
- RBQE
- AI models
- SegFormer-B0MedSAMUNet++
From the original article
1 min read at arxiv.orgIn real-time colonoscopy, ground-truth annotations are unavailable at inference, so polyp segmentation models can fail silently. We propose Referee-Based Quality Estimation (RBQE), a reference-free framework measuring agreement between a primary segmentation model and an independently trained referee on the same image.
By Siddharth Gupta · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.