为什么SSD要比YOLO快?

SSD原文中说The fundamental improvement in speed comes from eliminating bounding box proposals and the subsequent pixel or feature resampling stage.能否详细说明下
已邀请:

penguin企 - 学习深度学习

赞同来自: bea_tree caffe 调参小白

文中有句话:if we use the whole topmost feature map and add a
fully connected layer for predictions instead of our convolutional predictors, and do not
explicitly consider multiple aspect ratios, we can approximately reproduce YOLO
yolo要再整个最顶层featuremap上预测,ssd只预测默认的anchor。另外,yolo后面还有一层全连接,ssd后面是卷积,应该卷积比较快

要回复问题请先登录注册