Deeply-Supervised Nets

Deeply-Supervised Nets

Chen-Yu Lee,  Saining Xie,  Patrick Gallagher,  Zhengyou Zhang,  Zhuowen Tu

Our proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent. We make an attempt toboostthe classification performance by studying a new formulation in deep networks. Three aspects in convolutional neural networks (CNN) style architectures are being looked at: (1) transparency of the intermediate layers to the overall classification; (2) discriminativeness and robustness of learned features, especially in the early layers; (3) effectiveness in training due to the presence of the exploding and vanishing gradients. We introduce "companion objective" to the individual hidden layers, in addition to the overall objective at the output layer (a different strategy to layer-wise pre-training). We extend techniques from stochastic gradient methods to analyze our algorithm. The advantage of our method is evident and our experimental result on benchmark datasets shows significant performance gain over existing methods (e.g. all state-of-the-art results on MNIST, CIFAR-10, CIFAR-100, and SVHN).

示意图：

prototxt解析:

其中cccp layer是1*1kernel convolution层。。

paper下载：http://arxiv.org/abs/1409.5185

code 和prototxt文件下载：https://github.com/s9xie/DSN