Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation

First seen · 9/10/2026, 01:32 AMLatest activity · 9/10/2026, 01:32 AM

Deploying polyp segmentation models during real-time colonoscopy carries the risk of silent inference failures due to the absence of ground-truth annotations. This work introduces Referee-Based Quality Estimation (RBQE), a reference-free framework that assesses segmentation confidence via agreement with an independently trained referee model. Evaluated on a 1,223-image multi-dataset benchmark, a lightweight SegFormer-B0 referee achieves an ROC-AUC of 0.960—outperforming test-time augmentation while requiring only a single extra deterministic forward pass. Even after filtering out trivial empty-mask cases, cross-model agreement reliably flags unreliable outputs and enhances the precision of selective prediction.

Event heat · last 24 hours

There are 7 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 11:00; latest heat is 0.

There are 7 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 11:00; latest heat is 0.10.509/12, 11:00, event heat 09/12, 14:00, event heat 09/12, 17:00, event heat 09/12, 20:00, event heat 09/12, 23:00, event heat 09/13, 02:00, event heat 09/13, 05:00, event heat 024 hours agoNow
  1. 9/12, 11:00, event heat 0
  2. 9/12, 14:00, event heat 0
  3. 9/12, 17:00, event heat 0
  4. 9/12, 20:00, event heat 0
  5. 9/12, 23:00, event heat 0
  6. 9/13, 02:00, event heat 0
  7. 9/13, 05:00, event heat 0

Reporting Timeline

  1. AggregatorarXiv9/10, 01:32 AMnot independentRepresentative
    Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation