Efficient densely connected convolutional neural networks
Pattern Recognition(2021)
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.
更多查看译文
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