Detecting Twenty-thousand Classes using Image-level Supervision

Benchmark Model Rank Results
cross-domain-few-shot-object-detection-on-neu-detDetic-FT#3mAP: 16.8
cross-domain-few-shot-object-detection-on-neu-detDetic(w/o FT)#10mAP: 0.0
cross-domain-few-shot-object-detection-on-uoddDetic-FT#3mAP: 16.8
cross-domain-few-shot-object-detection-on-uoddDetic(w/o FT)#13mAP: 0.0
cross-domain-few-shot-object-detection-on-deepfishDetic-FT#7mAP: 17.9
cross-domain-few-shot-object-detection-on-deepfishDetic(w/o FT)#10mAP: 0.9
cross-domain-few-shot-object-detection-on-clipark1kDetic-FT#8mAP: 22.3
cross-domain-few-shot-object-detection-on-clipark1kDetic(w/o FT)#9mAP: 11.4
cross-domain-few-shot-object-detection-on-diorDetic-FT#10mAP: 15.4
cross-domain-few-shot-object-detection-on-diorDetic(w/o FT)#13mAP: 0.1
cross-domain-few-shot-object-detection-on-artaxorDetic-FT#11mAP: 12.0
cross-domain-few-shot-object-detection-on-artaxorDetic(w/o FT)#13mAP: 0.6
open-vocabulary-object-detection-on-lvis-v1-0Detic#26AP novel-LVIS base training: 17.8
open-vocabulary-object-detection-on-mscocoDetic#26AP 0.5: 27.8