2019-05-28-VGG（Very Deep Convolutional Networks for Large-Scale Image Recognition）

1. 研究背景
   • investigate the effect of the convolutional network depth on its
     accuracy
2. 创新点
   • a thorough evaluation of networks of increasing depth using an architecture with very small (3×3) convolution filters

3. 算法框架

   
   
   

   VGG
4. 实现细节
   • 3个3×3卷积核相比1个7×7卷积核的优势
     • make the decision function morediscriminative by incorporating three non-linear rectification layers
     • decrease the number of parameters
   • 网络D比C更具优势的原因
     • while the additional non-linearity does help (C is better than B), it is also important to capture spatial context by using conv. filters with non-trivial receptive fields (D is better than C)