OPeN (ResNet-152)

Reported on 5 benchmarks across 5 tasks · 1 paper

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

Methodology3 results

Generalized Few-Shot ClassificationonPlaces-LT
Top-1 Accuracy· 2021-12-16
40.5
best: 53.7 (LIFT (ViT-L/14))
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images arXiv:2112.08810
Long-tail LearningonPlaces-LT
Top-1 Accuracy· 2021-12-16
40.5
best: 53.7 (LIFT (ViT-L/14))
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images arXiv:2112.08810
Generalized Few-Shot LearningonPlaces-LT
Top-1 Accuracy· 2021-12-16
40.5
best: 53.7 (LIFT (ViT-L/14))
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images arXiv:2112.08810

Computer Vision2 results

Image ClassificationonPlaces-LT
Top-1 Accuracy· 2021-12-16
40.5
best: 53.7 (LIFT (ViT-L/14))
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images arXiv:2112.08810
Few-Shot Image ClassificationonPlaces-LT
Top-1 Accuracy· 2021-12-16
40.5
best: 53.7 (LIFT (ViT-L/14))
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images arXiv:2112.08810