IDeMe-Net (ResNet-50)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image ClassificationonImageNet-FS (1-shot, novel)
Top-5 Accuracy (%)· 2019-05-28
60.1
best: 62.73 (KGTN-ens (ResNet-50, h+g, max))
SOTA
Image Deformation Meta-Networks for One-Shot Learning arXiv:1905.11641
Image ClassificationonImageNet-FS (2-shot, novel)
Top-5 Accuracy (%)· 2019-05-28
69.6
best: 71.48 (KGTN-ens (ResNet-50, h+g, max))
SOTA
Image Deformation Meta-Networks for One-Shot Learning arXiv:1905.11641
Few-Shot Image ClassificationonImageNet-FS (1-shot, novel)
Top-5 Accuracy (%)· 2019-05-28
60.1
best: 62.73 (KGTN-ens (ResNet-50, h+g, max))
SOTA
Image Deformation Meta-Networks for One-Shot Learning arXiv:1905.11641
Few-Shot Image ClassificationonImageNet-FS (2-shot, novel)
Top-5 Accuracy (%)· 2019-05-28
69.6
best: 71.48 (KGTN-ens (ResNet-50, h+g, max))
SOTA
Image Deformation Meta-Networks for One-Shot Learning arXiv:1905.11641