CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection
Open World Object Detection (OWOD) built on multimodal foundation models often suffers from semantic ambiguity caused by unidirectional text-to-vision matching, while rigid outlier penalties may over-suppress unknown objects near known-class decision boundaries. We propose CODE (Cross-Modal Calibration and Dynamic Suppression), a unified inference-time framework with three complementary components. Cross-Modal Joint Confidence Calibration injects global visual prototypes to calibrate text-driven known-class predictions. Uncertainty-Guided Universal Objectness Enhancement measures classificatio
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%Into the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning →
- FuzzyOverlapping authors or contributors · 62%keras-team/keras →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%HKUDS/LightRAG →
“Shared author/contributor keys: jin”
- LinkedLinked via arxiv author · 85%Zhichao Xu →
“CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection”
- LinkedLinked via arxiv author · 85%Zhaoning Shi →
“CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection”
- LinkedLinked via arxiv author · 85%Hehe Jin →
“CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection”
- LinkedLinked via arxiv author · 85%Bo Ma →
“CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection”