KTCH (ResNet-50)

Reported on 6 benchmarks across 2 tasks · 1 paper

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

Computer Vision6 results

Image ClassificationonImageNet-FS (5-shot, all)
Top-5 Accuracy (%)· 2022-10-13
77.6
best: 81.12 (KGTN-ens (ResNet-50, h+g, max))
Few-shot Relational Reasoning via Connection Subgraph Pretraining arXiv:2210.06722
Image ClassificationonImageNet-FS (1-shot, novel)
Top-5 Accuracy (%)· 2022-10-13
58.1
best: 62.73 (KGTN-ens (ResNet-50, h+g, max))
Few-shot Relational Reasoning via Connection Subgraph Pretraining arXiv:2210.06722
Image ClassificationonImageNet-FS (2-shot, novel)
Top-5 Accuracy (%)· 2022-10-13
67.3
best: 71.48 (KGTN-ens (ResNet-50, h+g, max))
Few-shot Relational Reasoning via Connection Subgraph Pretraining arXiv:2210.06722
Few-Shot Image ClassificationonImageNet-FS (5-shot, all)
Top-5 Accuracy (%)· 2022-10-13
77.6
best: 81.12 (KGTN-ens (ResNet-50, h+g, max))
Few-shot Relational Reasoning via Connection Subgraph Pretraining arXiv:2210.06722
Few-Shot Image ClassificationonImageNet-FS (1-shot, novel)
Top-5 Accuracy (%)· 2022-10-13
58.1
best: 62.73 (KGTN-ens (ResNet-50, h+g, max))
Few-shot Relational Reasoning via Connection Subgraph Pretraining arXiv:2210.06722
Few-Shot Image ClassificationonImageNet-FS (2-shot, novel)
Top-5 Accuracy (%)· 2022-10-13
67.3
best: 71.48 (KGTN-ens (ResNet-50, h+g, max))
Few-shot Relational Reasoning via Connection Subgraph Pretraining arXiv:2210.06722