DenseNet, short for Dense Convolutional Network, is a deep learning architecture for convolutional neural networks (CNNs) introduced by Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger in their paper titled "Densely Connected Convolutional Networks" published in 2017.
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.
Dense Convolutional Network (DenseNet), 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.
DenseNet proposed a novel way of connecting layers that significantly improved gradient flow, reduced redundancy, and enhanced feature reuse. In traditional deep convolutional neural networks...
If you use DenseNet as a model in your learning task, to reduce the memory and time consumption, we recommend use a wide and shallow DenseNet, following the strategy of wide residual networks.
DenseNet (dense convolutional network) is to some extent the logical extension of this (Huang et al., 2017). DenseNet is characterized by both the connectivity pattern where each layer connects to all the preceding layers and the concatenation operation (rather than the addition operator in ResNet) to preserve and reuse features from earlier ...
8.7. Densely Connected Networks (DenseNet) — Dive into Deep ... - D2L
DenseNet was originally proposed in a paper titled “ Densely Connected Convolutional Networks ” written by Gao Huang et al. back in 2016 [1]. The main idea of DenseNet is indeed to solve the vanishing gradient problem.