Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection

Benchmark Model Rank Results
open-vocabulary-attribute-detection-on-ovadObject-Centric-OVD (ResNet50)#5mean average precision: 14.6
open-vocabulary-object-detection-on-lvis-v1-0Object-Centric-OVD#22AP novel-LVIS base training: 21.1
open-vocabulary-object-detection-on-mscocoObject-Centric-OVD#15AP 0.5: 36.9
zero-shot-object-detection-on-mscocoObject-Centric-OVD#6AP: 40.5