Efficient densely connected convolutional neural networks

Guoqing Li,Meng Zhang,Jiaojie Li,Feng Lv,Guodong Tong

Pattern Recognition（2021）

引用 51|浏览23

暂无评分

摘要

•Proposed two efficient densely connected ConvNets, DesneDsc and Dense2Net.•DesneDsc and Dense2Net are more efficient and have higher accuracy than DenseNet.•Dense2Net are state-of-the-art on ImageNet in manual CNNs with <10 M parameters.•DenseDsc and Dense2Net are very flexible and can be used in different applications.

查看译文

关键词

Convolutional neural networks,Classification,Parameter efficiency,Densely connected

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要