Shortcuts

DenseNet

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 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.

How to use it?

from mmpretrain import inference_model

predict = inference_model('densenet121_3rdparty_in1k', 'demo/bird.JPEG')
print(predict['pred_class'])
print(predict['pred_score'])

Models and results

Image Classification on ImageNet-1k

Model

Pretrain

Params (M)

Flops (G)

Top-1 (%)

Top-5 (%)

Config

Download

densenet121_3rdparty_in1k*

From scratch

7.98

2.88

74.96

92.21

config

model

densenet169_3rdparty_in1k*

From scratch

14.15

3.42

76.08

93.11

config

model

densenet201_3rdparty_in1k*

From scratch

20.01

4.37

77.32

93.64

config

model

densenet161_3rdparty_in1k*

From scratch

28.68

7.82

77.61

93.83

config

model

Models with * are converted from the official repo. The config files of these models are only for inference. We haven’t reproduce the training results.

Citation

@misc{https://doi.org/10.48550/arxiv.1608.06993,
      doi = {10.48550/ARXIV.1608.06993},
      url = {https://arxiv.org/abs/1608.06993},
      author = {Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q.},
      keywords = {Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
      title = {Densely Connected Convolutional Networks},
      publisher = {arXiv},
      year = {2016},
      copyright = {arXiv.org perpetual, non-exclusive license}
}
Read the Docs v: latest
Versions
latest
stable
mmcls-1.x
mmcls-0.x
dev
Downloads
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.