Densely Connected Convolutional Networks

Citations Over TimeTop 1% of 2017 papers

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 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 (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.

Related Papers

• → Hyperspectral Images Classification With Gabor Filtering and Convolutional Neural Network(2017)264 cited
• → An Approach for Multi Label Image Classification Using Single Label Convolutional Neural Network(2018)12 cited
• → Densely Connected Convolutional Networks(2016)1,897 cited
• → Good Practice in CNN Feature Transfer(2016)127 cited
• → Convolutional Networks with Dense Connectivity(2020)9 cited