Can I read Densely Connected Convolutional Networks on EtoBox?

Densely Connected Convolutional Networks by Gao Huang; Zhuang Liu; Laurens Van Der Maaten; Kilian Q. Weinberger is a scholarly article available to read on EtoBox.

What is Densely Connected Convolutional Networks about?

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections-one between each layer and its subsequent layer-our network has L(L+1) 2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance. Code and pre-traine

Author

Gao Huang; Zhuang Liu; Laurens Van Der Maaten; Kilian Q. Weinberger

Publisher

IEEE

Published

2017

Language

EN