Table 2 The accuracy performance (%) of three backbone networks on the VeRi776 [1] dataset and the VehicleID [2] dataset
From: Viewpoint robust knowledge distillation for accelerating vehicle re-identification
Backbone Networks | Using VRKD | Training Tricks | VeRi776 | VehicleID | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Â | Â | Â | Â | Â | Â | Test800 | Test1600 | Test2400 | |||
| Â | Â | LS=1 | LSR | MAP | R1 | MAP | R1 | MAP | R1 | MAP | R1 |
DenseNet121 [16] | No | No | Yes | 54.26 | 85.64 | 78.84 | 72.22 | 75.84 | 69.70 | 73.01 | 66.98 |
ResNet-18 [15] | No | No | Yes | 68.03 | 92.37 | 84.04 | 77.51 | 79.93 | 73.39 | 77.40 | 70.74 |
ResNet-50 [15] | No | No | Yes | 73.98 | 95.05 | 87.36 | 81.31 | 83.50 | 77.27 | 80.94 | 74.35 |