MetaFun-Attention

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 ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2019-12-05
80.82
best: 98.72 (SgVA-CLIP)
MetaFun: Meta-Learning with Iterative Functional Updates arXiv:1912.02738
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2019-12-05
64.13
best: 97.95 (SgVA-CLIP)
MetaFun: Meta-Learning with Iterative Functional Updates arXiv:1912.02738
Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2019-12-05
67.72
best: 96.8 (CAML [Laion-2b])
MetaFun: Meta-Learning with Iterative Functional Updates arXiv:1912.02738
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2019-12-05
80.82
best: 98.72 (SgVA-CLIP)
MetaFun: Meta-Learning with Iterative Functional Updates arXiv:1912.02738
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2019-12-05
64.13
best: 97.95 (SgVA-CLIP)
MetaFun: Meta-Learning with Iterative Functional Updates arXiv:1912.02738
Few-Shot Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2019-12-05
67.72
best: 96.8 (CAML [Laion-2b])
MetaFun: Meta-Learning with Iterative Functional Updates arXiv:1912.02738