Title | ||
---|---|---|
Topological optimization of the DenseNet with pretrained-weights inheritance and genetic channel selection |
Abstract | ||
---|---|---|
•A GA training pipeline to select key input channels of DenseNet automatically.•A ’Weight inheritance’ strategy to improve efficiency whilst maintaining accuracy.•To reduce up to 30% parameters yet achieving a similar accuracy as the DenseNet.•Validated robustness/scalability on several image recognition/classification datasets. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.patcog.2020.107608 | Pattern Recognition |
Keywords | DocType | Volume |
Deep convolutional neural networks,Genetic algorithms,Parameter reduction,Structure optimization,DenseNet | Journal | 109 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 24 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhenyu Fang | 1 | 3 | 1.77 |
Jinchang Ren | 2 | 1144 | 88.54 |
Stephen Marshall | 3 | 35 | 3.22 |
Huimin Zhao | 4 | 206 | 23.43 |
Song Wang | 5 | 954 | 79.55 |
Xuelong Li | 6 | 15049 | 617.31 |