Few Shot Image Classification On Imagenet Fs
Metrics
Top-5 Accuracy (%)
Results
Performance results of various models on this benchmark
Model Name | Top-5 Accuracy (%) | Paper Title | Repository |
|---|---|---|---|
| LSD (ResNet-50) | 57.7 | Low-shot learning with large-scale diffusion | |
| SGM + Graph (ResNet-50) | 61.1 | Model-Agnostic Graph Regularization for Few-Shot Learning | - |
| IDeMe-Net (ResNet-50) | 60.1 | Image Deformation Meta-Networks for One-Shot Learning | |
| SGM (ResNet-50) | 52.9 | Low-shot Visual Recognition by Shrinking and Hallucinating Features | |
| KGTN-ens (ResNet-50, h+g, max) | 62.73 | KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles | |
| KTCH (ResNet-50) | 58.1 | Few-shot Relational Reasoning via Connection Subgraph Pretraining | |
| KGTN (ResNet-50) | 62.1 | Knowledge Graph Transfer Network for Few-Shot Recognition |
0 of 7 row(s) selected.