CVLGAug 25, 2016

Densely Connected Convolutional Networks

arXiv:1608.06993v543205 citationsHas Code
Originality Highly original
AI Analysis

This addresses the challenge of vanishing gradients and parameter efficiency in deep learning for computer vision, offering a novel architecture that enhances performance on competitive benchmarks.

The paper tackles the problem of training deep convolutional networks by introducing DenseNet, which connects each layer to every other layer, resulting in significant improvements over state-of-the-art on object recognition benchmarks like CIFAR-10, CIFAR-100, SVHN, and ImageNet, with less computation required.

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 computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet .

Code Implementations146 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes