Densely Connected Convolutional Networks Gao Huang∗ Cornell University gh349@cornell.edu Zhuang Liu∗ Tsinghua University liuzhuangthu@gmail.com Kilian Q. Weinberger Cornell University kqw4@cornell.edu Laurens van der Maaten Facebook AI Research lvdmaaten@fb.com Abstract 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 Convo- lutional 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
