2018 CVPR
Acquisition of Localization Confidence for Accurate Object Detection
PreciseRoIPooling 代码
ECCV 2018 | 旷视科技 Oral 论文解读:IoU-Net 让目标检测用上定位置信度
建议先自己看一遍论文,然后再看下面的总结
IoU-Net
解决问题 : nms 过程中,是挑选 分类置信度最大的值的框,但是它不一定框的准
Two drawbacks in object localization
- the misalignment between classification confidence and localization accuracy
- the non-monotonic bounding box regression
joint training
-
Backbone
ResNet-FPN -
FPN
-
Precise RoI Pooling
-
Head
works in parallel
based on the same visual feature from the backbone- IoU predictor
- R-CNN
- classification and regression brance take 512 RoIs per image from RPNs