TRAML

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

Image ClassificationonImageNet (1-shot)
Top-5 Accuracy· 2020-05-28
59.2
SOTA
Boosting Few-Shot Learning With Adaptive Margin Loss arXiv:2005.13826
Few-Shot Image ClassificationonImageNet (1-shot)
Top-5 Accuracy· 2020-05-28
59.2
SOTA
Boosting Few-Shot Learning With Adaptive Margin Loss arXiv:2005.13826
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2020-05-28
79.54
best: 98.72 (SgVA-CLIP)
Boosting Few-Shot Learning With Adaptive Margin Loss arXiv:2005.13826
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2020-05-28
67.1
best: 97.95 (SgVA-CLIP)
Boosting Few-Shot Learning With Adaptive Margin Loss arXiv:2005.13826
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2020-05-28
79.54
best: 98.72 (SgVA-CLIP)
Boosting Few-Shot Learning With Adaptive Margin Loss arXiv:2005.13826
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2020-05-28
67.1
best: 97.95 (SgVA-CLIP)
Boosting Few-Shot Learning With Adaptive Margin Loss arXiv:2005.13826