Research Article
MFOC-CliqueNet: A CliqueNet-Based Optimal Combination of Multidimensional Features Classification Method for Large-Scale Laser Point Clouds
Table 1
MFOC-CliqueNet network design.
| Layer | S |
| Convolution | Conv (5 × 5), 64, stride 2 | Pooling | Max pool (3 × 3), stride 2 | Block 1 | 36 × 5 | 36 × 5 | 36 × 5 | 40 × 6 |
| Transition: conv (1 × 1), avg pool (2 × 2) | Block 2 | 64 × 6 | 80 × 6 | 80 × 5 | 80 × 6 |
| Transition: conv (1 × 1), avg pool (2 × 2) | Block 3 | 100 × 6 | 120 × 6 | 150 × 6 | 160 × 6 |
| Transition: conv (1 × 1), avg pool (2 × 2) | Block 4 | 80 × 6 | 100 × 6 | 120 × 6 | 160 × 6 |
|
|