Comparison of computational performance results of different feature extraction networks
| Method | Parameters (M) | Iteration time per step (s) |
|---|---|---|
| DB | 61.74 | 4.02 |
| RDB (Zhang et al., 2018) | 51.63 | 3.99 |
| MRDB (ours) | 48.12 | 2.99 |
| Method | Parameters (M) | Iteration time per step (s) |
|---|---|---|
| DB | 61.74 | 4.02 |
| RDB ( | 51.63 | 3.99 |
Note(s): RDB represents residual dense block, which is well applied in neural network's backbone. The best results are highlighted in italics
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.