cascade R-CNN

级联R-CNN为了解决目标检测中IOU阈值选取问题而提出,通过一系列IOU逐渐增大的检测器,逐步提高提案的准确性。在保证样本数量的同时训练高质量检测器,从而提高性能。文章介绍了级联R-CNN的出现原因、解决方法及其带来的性能提升。
摘要由CSDN通过智能技术生成

级联R-CNN出现原因

论文链接:https://arxiv.org/abs/1712.00726
上文针对目标检测中IOU阈值选取问题。一味增大阈值,使得样本减少。容易导致过拟合。且train和inference阶段的阈值不同导致更严重的mismatch.
回顾faster R-CNN:
train阶段:将整张图片喂入conv-relu-pooling得到整各特征图,再RPN选取2000个proposals,通过softmax判断锚点(anchors (目标框))判断是否为前景(是否有物体),边界框回归筛选精确proposals,proposals(128个)被送入到Roi Pooling,提取目标区域的特征图,最后进行类别分类和box回归(判断是什么物体)
softmax 一次性分类多个物体。等价于多个SVM
faster R-CNN
inference阶段:RPN选取300左右proposals,送入fast R-CNN,和train阶段不同的是:无法确定gt,导致无法筛选proposals,全部送入Roi-Pooling
IoU:指真实框和预测框的关联度。由proposal和gt确定IOU。
inference:指test阶段或者predict阶段。
mismatch :training阶段的输入proposals质量更高(被采样过,IoU>threshold),inference阶段的输入proposals质量相对较差.导致

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection per- formance tends to degrade with increasing the IoU thresh- olds. Two main factors are responsible for this: 1) over- fitting during training, due to exponentially vanishing pos- itive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the in- put hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these prob- lems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selec- tive against close false positives. The detectors are trained stage by stage, leveraging the observation that the out- put of a detector is a good distribution for training the next higher quality detector. The resampling of progres- sively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reduc- ing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challeng- ing COCO dataset. Experiments also show that the Cas- cade R-CNN is widely applicable across detector architec- tures, achieving consistent gains independently of the base- line detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值