Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

ProCal: Inference-Time Proposal Calibration for Open-Vocabulary Object Detection

First seen · 7/2/2026, 02:18 PMLatest activity · 7/2/2026, 02:18 PM

ProCal is an inference-time proposal calibration method for open-vocabulary object detection. The method combines a localization-aware foreground score with a background-aware suppression score to form a proposal prior, improving the localization quality of classification scores from a frozen vision-language model. The authors report that, when applied to CLIPSelf ViT-L/14, ProCal improves APr by 2.5 on OV-LVIS. Their analysis attributes the gain to proposal-level reranking that suppresses false novel activations on background regions and ranks true novel proposals above background and partial-object proposals.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/2, 02:18 PMnot independentRepresentative
    ProCal: Inference-Time Proposal Calibration for Open-Vocabulary Object Detection