GPaCo (2-ResNeXt101-32x4d)

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 ClassificationonImageNet-LT
Top-1 Accuracy· 2022-09-26
63.2
best: 82.9 (LIFT (ViT-L/14))
Generalized Parametric Contrastive Learning arXiv:2209.12400
Long-tail LearningonImageNet-LT
Top-1 Accuracy· 2022-09-26
63.2
best: 82.9 (LIFT (ViT-L/14))
Generalized Parametric Contrastive Learning arXiv:2209.12400
Generalized Few-Shot LearningonImageNet-LT
Top-1 Accuracy· 2022-09-26
63.2
best: 82.9 (LIFT (ViT-L/14))
Generalized Parametric Contrastive Learning arXiv:2209.12400

Computer Vision2 results

Image ClassificationonImageNet-LT
Top-1 Accuracy· 2022-09-26
63.2
best: 82.9 (LIFT (ViT-L/14))
Generalized Parametric Contrastive Learning arXiv:2209.12400
Few-Shot Image ClassificationonImageNet-LT
Top-1 Accuracy· 2022-09-26
63.2
best: 82.9 (LIFT (ViT-L/14))
Generalized Parametric Contrastive Learning arXiv:2209.12400