Table 1.
A summary of four commonly used classic neural network models for image segmentation.
| AlexNet [27] | VGG [26] | GoogLeNet [28] | ResNet [29] | |
|---|---|---|---|---|
| Input Size | 227 × 227 | 224 × 224 | 224 × 224 | 224 × 224 |
| Number of Layers | 8 | 19 | 22 | 152 |
| Number of Conv. Layers | 5 | 16 | 21 | 151 |
| Filter Sizes | 3, 5, 11 | 3 | 1, 3, 5, 7 | 1, 3, 5, 7 |
| Strides | 1, 4 | 1 | 1, 2 | 1, 2 |
| Fully Connected Layers | 3 | 3 | 1 | 1 |
| TOP-5 Test Accuracy | 84.6% | 92.7% | 93.3% | 96.4% |
| Contributions | ReLU, Dropout | Small filter kernel | 1 × 1 Conv. | Residual learning |
| Advantages | Increase training speed and prevent overfitting | Suitable for parallel acceleration, nonlinear | Reduce the amount of computation | Overcome gradient vanishing |
| Disadvantages | Low accuracy | Small receptive field | Overfitting, vanishing gradient | Many parameters, long training time |