Fine-grained Image Classification on Aircrafts
74.55Top-1 AccuracyBYOL+CVSA
Evaluation results
| Method | Links | |
|---|---|---|
| BYOL+CVSABackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 74.55 | |
| BYOL+DiLoBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 73.52 | |
| InsLocBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 73.43 | |
| Rot-PredBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 72.67 | |
| BYOLBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 72.6 | |
| LooC*Backbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 72.49 | |
| SimCLRBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 72.42 | |
| Rel-LocBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 72.24 | |
| MoCo.v2Backbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06 | 71.93 | |
| RandomBackbone=ResNet-50, Pre-training Setting=Random initialization, Evaluation Protocol=Fine-tuned2021.06 | 70.58 |