Advances, Systems and Applications
Table 3 The proposed network vs popular networks in CIFAR-10
From: Lightweight image classifier using dilated and depthwise separable convolutions
Model | Classification | Parameters |
|---|---|---|
Accuracy | (Million) | |
3 ×1.0 224 this paper | 84.25% | 4.1 |
1.0 MobileNet 224 | 83.91% | 4.2 |
GoogleNet | 83.84% | 6.8 |
SqueezeNet | 69.83% | 1.25 |
VGG 16 | 86.17% | 138 |