RIDE (ResNeXt-50)

Reported on 5 benchmarks across 5 tasks · 1 paper · 5 SOTA

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

Methodology3 results

Generalized Few-Shot ClassificationonImageNet-LT
Top-1 Accuracy· 2020-10-05
56.4
best: 82.9 (LIFT (ViT-L/14))
SOTA
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts arXiv:2010.01809
Long-tail LearningonImageNet-LT
Top-1 Accuracy· 2020-10-05
56.4
best: 82.9 (LIFT (ViT-L/14))
SOTA
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts arXiv:2010.01809
Generalized Few-Shot LearningonImageNet-LT
Top-1 Accuracy· 2020-10-05
56.4
best: 82.9 (LIFT (ViT-L/14))
SOTA
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts arXiv:2010.01809

Computer Vision2 results

Image ClassificationonImageNet-LT
Top-1 Accuracy· 2020-10-05
56.4
best: 82.9 (LIFT (ViT-L/14))
SOTA
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts arXiv:2010.01809
Few-Shot Image ClassificationonImageNet-LT
Top-1 Accuracy· 2020-10-05
56.4
best: 82.9 (LIFT (ViT-L/14))
SOTA
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts arXiv:2010.01809