Convolutional Networks with Dense Connectivity

by   Gao Huang, et al.
Tsinghua University
cornell university
berkeley college

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, encourage feature reuse and substantially improve parameter efficiency. 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 parameters and computation to achieve high performance.


Densely Connected Convolutional Networks

Recent work has shown that convolutional networks can be substantially d...

Exploring Feature Reuse in DenseNet Architectures

Densely Connected Convolutional Networks (DenseNets) have been shown to ...

CondenseNet V2: Sparse Feature Reactivation for Deep Networks

Reusing features in deep networks through dense connectivity is an effec...

ChoiceNet: CNN learning through choice of multiple feature map representations

We introduce a new architecture called ChoiceNet where each layer of the...

Convolutional Networks with Adaptive Computation Graphs

Do convolutional networks really need a fixed feed-forward structure? Of...

Submanifold Sparse Convolutional Networks

Convolutional network are the de-facto standard for analysing spatio-tem...

ParaNet - Using Dense Blocks for Early Inference

DenseNets have been shown to be a competitive model among recent convolu...

Code Repositories


Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

view repo

Please sign up or login with your details

Forgot password? Click here to reset