Meta-GMVAE

Reported on 4 benchmarks across 2 tasks

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 5-way (1-shot)
Accuracy
42.82
best: 97.95 (SgVA-CLIP)
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy
55.73
best: 98.72 (SgVA-CLIP)
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy
42.82
best: 97.95 (SgVA-CLIP)
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy
55.73
best: 98.72 (SgVA-CLIP)