feat+ (ProtoNet-ResNet)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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 (5-shot)
Accuracy· 2018-12-10
78.38
best: 98.72 (SgVA-CLIP)
SOTA
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2018-12-10
78.38
best: 98.72 (SgVA-CLIP)
SOTA
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2018-12-10
61.72
best: 97.95 (SgVA-CLIP)
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2018-12-10
61.72
best: 97.95 (SgVA-CLIP)
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664