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

IoU-Net解决目标检测中分类置信度高但定位不准的问题,通过联合训练优化定位。文章介绍了IoU-Net的结构,包括ResNet-FPN、精确RoI池化和IoU预测器。训练过程使用smooth-L1损失,IoU标签归一化。在推断阶段,IoU指导的NMS优化边界框选择,提高检测准确性。
最低0.47元/天 解锁文章
2646

被折叠的 条评论
为什么被折叠?



