feat (ProtoNet)

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 ClassificationonCUB 200 5-way 5-shot
Accuracy· 2018-12-10
83.03
best: 98.7 (CAML [Laion-2b])
SOTA
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664
Few-Shot Image ClassificationonCUB 200 5-way 5-shot
Accuracy· 2018-12-10
83.03
best: 98.7 (CAML [Laion-2b])
SOTA
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664
Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2018-12-10
68.65
best: 95.8 (PT+MAP+SF+SOT (transductive))
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664
Few-Shot Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2018-12-10
68.65
best: 95.8 (PT+MAP+SF+SOT (transductive))
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions arXiv:1812.03664