DenseNet: Densely Connected CNN

最新推荐文章于 2022-02-25 18:47:35 发布

deepindeed

最新推荐文章于 2022-02-25 18:47:35 发布

阅读量414

点赞数

分类专栏：【计算机视觉】【论文笔记】文章标签： Paper

本文为博主原创文章，未经博主允许不得转载。

本文链接：https://blog.csdn.net/cwlseu/article/details/103744858

版权

本文详细介绍了DenseNet稠密连接卷积网络的原理和优势，包括残差网的关键技术、DenseNet的结构、增长速率、效果分析，以及在不同数据集上的表现。DenseNet通过层间密集连接减少了参数数量，提高了信息传播效率，解决了梯度消失问题，同时在分类错误率和计算量上优于ResNet。

摘要由CSDN通过智能技术生成

文章来源

arxiv
torch代码地址
 caffe模型地址

突出贡献

In this paper, we propose an architecture that distills this insight into a simple connectivity pattern: to ensure maximum information flow between layers in the network, we connect all layers (with matching feature-map sizes) directly with each other. To preserve the feed-forward nature, each layer obtains additional inputs from all preceding layers and passes on its own feature-maps to all subsequent
layers. Crucially, in contrast to ResNets, we never combine features
through summation before they are passed into a layer; instead, we combine features by concatenating them.