cvpr2016专题

Training Region-based Object Detectors with Online Hard Example Mining(CVPR2016 Oral)

转载自:http://zhangliliang.com/2016/04/13/paper-note-ohem/ Training Region-based Object Detectors with Online Hard Example Mining是CMU实验室和rbg大神合作的paper,cvpr16的oral,来源见这里:http://arxiv.org/pdf/1604.03540

FPN及其feature map特征融合(CVPR2016:Feature Pyramid Networks for Object Detection)

1 feature map的计算 以feature map的大小区分conv1 conv2 … 在conv1或conv2中feature map的大小是不变的,从conv1到conv2的某种操作feature map大小才会改变。 以VGG16为例,padding=0的池化操作改变feature map大小。 实际上在卷积或池化后: feature map size = output size