Libra R-CNN: Towards Balanced Learning for Object Detection

CVPR 2019 Jiangmiao PangKai ChenJianping ShiHuajun FengWanli OuyangDahua Lin

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)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Detection COCO minival Libra R-CNN (ResNet-50 FPN) box AP 38.5 # 50
AP50 59.3 # 31
AP75 42.0 # 32
APS 22.9 # 28
APM 42.1 # 31
APL 50.5 # 36
Object Detection COCO test-dev Libra R-CNN (ResNeXt-101-FPN) box AP 43.0 # 40
AP50 64 # 37
AP75 47 # 41
APS 25.3 # 44
APM 45.6 # 45
APL 54.6 # 45

Methods used in the Paper