High-End MAML++

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 ClassificationonCUB 200 5-way 5-shot
Accuracy· 2019-05-24
83.8
best: 98.7 (CAML [Laion-2b])
Learning to learn via Self-Critique arXiv:1905.10295
Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2019-05-24
67.48
best: 95.8 (PT+MAP+SF+SOT (transductive))
Learning to learn via Self-Critique arXiv:1905.10295
Few-Shot Image ClassificationonCUB 200 5-way 5-shot
Accuracy· 2019-05-24
83.8
best: 98.7 (CAML [Laion-2b])
Learning to learn via Self-Critique arXiv:1905.10295
Few-Shot Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2019-05-24
67.48
best: 95.8 (PT+MAP+SF+SOT (transductive))
Learning to learn via Self-Critique arXiv:1905.10295