Image Classification On Food 101 1
评估指标
Accuracy (%)
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| Bamboo (ViTB/16) | 92.9 | Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy | |
| SEER (RegNet10B - linear eval) | 90.3 | Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision | |
| TWIST (ResNet-50) | 89.3 | Self-Supervised Learning by Estimating Twin Class Distributions | |
| TransBoost-ResNet50 | 84.30 | TransBoost: Improving the Best ImageNet Performance using Deep Transduction | |
| NNCLR | 76.7 | With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations | |
| Inception V3 | 71.67 | Image and Text fusion for UPMC Food-101 \using BERT and CNNs | - |
0 of 6 row(s) selected.