LR+ICI

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

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image ClassificationonDirichlet Tiered-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2020-03-26
85.1
best: 86.6 (\alpha-TIM)
SOTA
Instance Credibility Inference for Few-Shot Learning arXiv:2003.11853
Image ClassificationonDirichlet Tiered-Imagenet (5-way, 1-shot)
1:1 Accuracy· 2020-03-26
74.6
best: 76.6 (BAVARDAGE)
SOTA
Instance Credibility Inference for Few-Shot Learning arXiv:2003.11853
Few-Shot Image ClassificationonDirichlet Tiered-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2020-03-26
85.1
best: 86.6 (\alpha-TIM)
SOTA
Instance Credibility Inference for Few-Shot Learning arXiv:2003.11853
Few-Shot Image ClassificationonDirichlet Tiered-Imagenet (5-way, 1-shot)
1:1 Accuracy· 2020-03-26
74.6
best: 76.6 (BAVARDAGE)
SOTA
Instance Credibility Inference for Few-Shot Learning arXiv:2003.11853