VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION——VGG
论文作者 KarenSimonyan & Andrew Zisserman
原文 点击打开链接
I. Features网络新特点
1. Very deep networks, large scale image recognition更深,数据集更大
2. Using small receptive field 更小的卷积核
a stack of two 3×3 conv.layers (without spatial pooling in between) has an effective receptive field of5×5; three such layers have a 7 × 7 effective receptivefield.
decreases the number of parameters : e.g. 72C2 = 49C2-->3(32C2)= 27C2
2. The incorporation of 1 × 1 conv. layers is away to incr