Research Article
CXR-RefineDet: Single-Shot Refinement Neural Network for Chest X-Ray Radiograph Based on Multiple Lesions Detection
Table 1
Performance comparison of different backbone networks.
| Backbone | mAP | Params (M) |
| All-Resblock | 0.1521 | 49.98 | All-RepVGG block | 0.1513 | 35.15 | ResNet-18 | 0.1409 | 30.16 | ResNet-34 | 0.1525 | 40.26 | REVGG-A0 | 0.1374 | 23.52 | REVGG-A1 | 0.1409 | 29.77 | REVGG-B0 | 0.1434 | 30.23 | REVGG-B1 | 0.1488 | 72.05 | RRNet (ours) | 0.1572 | 49.76 |
|
|