ProtoNet MTM SPSA-Track

Reported on 2 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 Vision2 results

Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-10-25
61.94
best: 97.95 (SgVA-CLIP)
Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning arXiv:2110.13188
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-10-25
61.94
best: 97.95 (SgVA-CLIP)
Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning arXiv:2110.13188