URT

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 ClassificationonMeta-Dataset
Accuracy· 2020-06-21
72.15
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
SOTA
A Universal Representation Transformer Layer for Few-Shot Image Classification arXiv:2006.11702
Few-Shot Image ClassificationonMeta-Dataset
Accuracy· 2020-06-21
72.15
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
SOTA
A Universal Representation Transformer Layer for Few-Shot Image Classification arXiv:2006.11702
Image ClassificationonMeta-Dataset Rank
Mean Rank· 2020-06-21
2.85
best: 11.8 (Relation Networks)
A Universal Representation Transformer Layer for Few-Shot Image Classification arXiv:2006.11702
Few-Shot Image ClassificationonMeta-Dataset Rank
Mean Rank· 2020-06-21
2.85
best: 11.8 (Relation Networks)
A Universal Representation Transformer Layer for Few-Shot Image Classification arXiv:2006.11702