Libra R-CNN: Towards Balanced Learning for Object Detection

Jiangmiao PangKai ChenJianping ShiHuajun FengWanli OuyangDahua Lin

   Papers with code   Abstract  PDF

Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
Libra R-CNN
(Faster R-CNN, ResNeXt…)
0.427
--
2
Libra R-CNN
(Faster R-CNN, ResNet-…)
0.403
--
3
Libra R-CNN
(Faster R-CNN, ResNet-…)
0.385
--
4
Libra R-CNN
(RetinaNet, ResNet-50-…)
0.377
--