SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection

Open paper
Benchmark Model Rank Results
object-detection-on-lvis-v1-0-valSimLTD w/MixPL (Swin-L + COCO unlabeled images)#8box AP: 51.5
object-detection-on-lvis-v1-0-valSimLTD Fully Supervised (Swin-L)#12box AP: 49.8box APr: 42.4

Rank counts only results with a code link.