Name
Abstract | ||
|---|---|---|
•We build a new standalone control module based on the scaled sigmoid function to enrich the neural network module family to enable the neural architecture optimization.•Our DNAL method produces no candidate neural architectures but one, thus drastically improving the learning efficiency, i.e., costing 20 epochs for CIFAR-10 and 10 epochs for ImageNet.•It is applicable to conventional CNNs, lightweight CNNs, and stochastic supernets.•Extensive experiments confirm that our DNAL method achieves excellent performance on various CNN architectures, including VGG16, ResNet50, MobileNetV2, and ProxylessNAS, over the task of CIFAR-10 and ImageNet-1K classification. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1016/j.patcog.2021.108448 | Pattern Recognition |
Keywords | DocType | Volume |
Deep neural network,Convolutional neural network,Neural architecture search,Automated machine learning | Journal | 126 |
ISSN | Citations | PageRank |
0031-3203 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qingbei Guo | 1 | 1 | 1.45 |
| Xiaojun Wu | 2 | 356 | 52.89 |
| J. Kittler | 3 | 14346 | 1465.03 |
| Zhiquan Feng | 4 | 36 | 13.73 |