The Detector Teaches Itself: Lightweight Self-Supervised Adaptation for Open-Vocabulary Object Detection

Open paper
Benchmark Model Rank Results
novel-object-detection-on-lvis-v1-0-valDAT–All mAP: 20.37Known mAP: 45.82Novel mAP: 17.68
open-vocabulary-object-detection-on-mscocoDAT–AP 0.5: 70.1

Rank counts only results with a code link.