UpperCaSE-ResNet50

Reported on 3 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 Vision3 results

Image ClassificationonVTAB-1k
Top-1 Accuracy· 2022-06-20
56.6
best: 79.99 (ALIGN (50 hypers/task))
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification arXiv:2206.09843
Image ClassificationonMeta-Dataset
Accuracy· 2022-06-20
74.9
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification arXiv:2206.09843
Few-Shot Image ClassificationonMeta-Dataset
Accuracy· 2022-06-20
74.9
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification arXiv:2206.09843