Meta LSTM, (from )

Reported on 4 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 Vision4 results

Image ClassificationonMini-Imagenet 20-way (1-shot)
Accuracy· 2017-07-31
16.7
best: 39.3 (TIM-GD)
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning arXiv:1707.09835
Image ClassificationonMini-Imagenet 20-way (5-shot)
Accuracy· 2017-07-31
26.06
best: 59.5 (TIM-GD)
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning arXiv:1707.09835
Few-Shot Image ClassificationonMini-Imagenet 20-way (1-shot)
Accuracy· 2017-07-31
16.7
best: 39.3 (TIM-GD)
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning arXiv:1707.09835
Few-Shot Image ClassificationonMini-Imagenet 20-way (5-shot)
Accuracy· 2017-07-31
26.06
best: 59.5 (TIM-GD)
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning arXiv:1707.09835