【目标检测】SPP-Net (Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition)
K.He,X.Zhang,S.Ren,andJ.Sun.Spatialpyramidpoolingindeepconvolutionalnetworksforvisualrecognition.InECCV,2014.Kaiming的这篇paper,是在R-CNN的基础上提出了空间金字塔变换层(SpatialPyramidPooling),SPPNet大幅度提高了R-CNN的训练速度和测试速度,同