Skip to main content

Table 9 RetinaNet (focal loss) on COCO [88]

From: Survey on deep learning with class imbalance

  Backbone AP \(AP_{50}\) \(AP_{75}\) \(AP_{S}\) \(AP_{M}\) \(AP_{L}\)
Two-stage methods
 Faster R-CNN+++ ResNet-101-C4 34.9 55.7 37.4 15.6 38.7 50.9
 Faster R-CNN w FPN ResNet-101-FPN 36.2 59.1 39.0 18.2 39.0 48.2
 Faster R-CNN by G-RMI Inception-ResNet-v2 34.7 55.5 36.7 13.5 38.1 52.0
 Faster R-CNN w TDM Inception-ResNet-v2-TDM 36.8 57.7 39.2 16.2 39.8 52.1
One-stage methods
 YOLOv2 DarkNet-19 21.6 44.0 19.2 5.0 22.4 35.5
 SSD513 ResNet-101-SSD 31.2 50.4 33.3 10.2 34.5 49.8
 DSSD513 ResNet-101-DSSD 33.2 53.3 35.2 13.0 35.4 51.1
 RetinaNet ResNet-101-FPN 39.1 59.1 42.3 21.8 42.7 50.2
 RetinaNet ResNeXt-101-FPN 40.8 61.1 44.1 24.1 44.2 51.2
  1. Italic scores indicate top AP performances