A differentiable IoU loss layer for rotated 2D and 3D bounding boxes improves SECOND, PointPillars, and PointRCNN on KITTI relative to the standard L1 regression loss.
Faster r-cnn: Towards real-time object detection with region proposal networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IoU Loss for 2D/3D Object Detection
A differentiable IoU loss layer for rotated 2D and 3D bounding boxes improves SECOND, PointPillars, and PointRCNN on KITTI relative to the standard L1 regression loss.