Title | ||
---|---|---|
Hybrid pooling for enhancement of generalization ability in deep convolutional neural networks. |
Abstract | ||
---|---|---|
•Hybrid pooling is proposed for improving the generalization ability of convolutional neural networks.•The performance of the hybrid pooling is presented in image classification tasks.•The hybrid pooling combined with the dropout technique is competitive to other methods.•Layer-wise control of feature extraction can be realized by the hybrid pooling. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.neucom.2018.12.036 | Neurocomputing |
Keywords | Field | DocType |
Deep learning,Pooling methods,Image recognition | Object detection,Pattern recognition,Convolutional neural network,Pooling,Curse of dimensionality,Artificial intelligence,Contextual image classification,Mathematics,Machine learning | Journal |
Volume | ISSN | Citations |
333 | 0925-2312 | 0 |
PageRank | References | Authors |
0.34 | 17 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhiqiang Tong | 1 | 0 | 0.34 |
Gouhei Tanaka | 2 | 51 | 11.80 |