Fine-grained Image Classification on iNaturalist 2018
87.5Top-1 AccMetaFormer
Evaluation results
| Method | Links | |
|---|---|---|
| MetaFormerBackbone=MetaFormer-1, Pretrain=iNat212022.03 | 87.5 | |
| MetaFormerBackbone=MetaFormer-1, Pretrain=ImageNet-21k2022.03 | 83.2 | |
| MetaFormerBackbone=MetaFormer-1, Pretrain=ImageNet-1k2022.03 | 81.9 | |
| GrafitBackbone=RegNet-8GF, Pretrain=ImageNet-1k2022.03 | 81.2 | |
| DeiT-BBackbone=ViT-B-16, Pretrain=ImageNet-21k2022.03 | 80.1 | |
| SwAVEvaluation protocol=linear classifier on fixed features, multi-crop=true2021.03 | 48.6 | |
| BYOLEvaluation protocol=linear classifier on fixed features2021.03 | 47.6 | |
| SupervisedEvaluation protocol=linear classifier on fixed features2021.03 | 46.7 | |
| BARLOW TWINSEvaluation protocol=linear classifier on fixed features2021.03 | 46.5 | |
| SwAVEvaluation protocol=linear classifier on fixed features, multi-crop=false2021.03 | 39.5 | |
| MoCo-v2Evaluation protocol=linear classifier on fixed features2021.03 | 38.6 | |
| SimCLREvaluation protocol=linear classifier on fixed features2021.03 | 37.2 |