Image Classification 벤치마크
Image Classification on Tiny-ImageNet
Top 1 Accuracy
- 2020-09-15 — PreActResNet18: Top 1 Accuracy 63.48
- 2021-03-15 — UPANets: Top 1 Accuracy 67.67
| Rank | Model | Top 1 Accuracy | Top-1 Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|---|
| 1 | UPANets | 67.67 | – | UPANets: Learning from the Universal Pixel Attention Networks | hanktseng131415go/UPANets | 2021 |
| 2 | PreActResNet18 | 63.48 | – | Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup | snu-mllab/PuzzleMix | 2020 |
| 3 | DLME (ResNet-18, linear) | 44.9 | – | DLME: Deep Local-flatness Manifold Embedding | Westlake-AI/openmixup · zangzelin/code_ECCV2022_DLME | 2022 |
| 4 | MMA-CCT-7/3x2 | – | 64.41 | Multi-manifold Attention for Vision Transformers | 2022 |