Category-Aware Dynamic Label Assignment with High-Quality Oriented Proposal
Open paper
Benchmark
Model
Rank
Results
object-detection-in-aerial-images-on-dota
CDLA-HOP
–
mAP: 82.02%
object-detection-in-aerial-images-on-hrsc2016
CDLA-HOP
–
mAP-07: 90.89
mAP-12: 98.77
Rank counts only results with a code link.