Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/LDAM + DRW + SAM

LDAM + DRW + SAM

Reported on 20 benchmarks across 5 tasks · 1 paper · 9 SOTA

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

Methodology12 results

Generalized Few-Shot ClassificationoniNaturalist 2018
Top-1 Accuracy· 2022-12-28
70.1
best: 74.8 (APA (SE-ResNet-50))
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Generalized Few-Shot ClassificationonCIFAR-10-LT (ρ=200)
Error Rate· 2022-12-28
21.9
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Long-tail LearningoniNaturalist 2018
Top-1 Accuracy· 2022-12-28
70.1
best: 74.8 (APA (SE-ResNet-50))
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Long-tail LearningonCIFAR-10-LT (ρ=200)
Error Rate· 2022-12-28
21.9
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Generalized Few-Shot LearningoniNaturalist 2018
Top-1 Accuracy· 2022-12-28
70.1
best: 74.8 (APA (SE-ResNet-50))
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Generalized Few-Shot LearningonCIFAR-10-LT (ρ=200)
Error Rate· 2022-12-28
21.9
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Generalized Few-Shot ClassificationonCIFAR-10-LT (ρ=10)
Error Rate· 2022-12-28
10.6
best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Generalized Few-Shot ClassificationonImageNet-LT
Top-1 Accuracy· 2022-12-28
53.1
best: 82.9 (LIFT (ViT-L/14))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Long-tail LearningonCIFAR-10-LT (ρ=10)
Error Rate· 2022-12-28
10.6
best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Long-tail LearningonImageNet-LT
Top-1 Accuracy· 2022-12-28
53.1
best: 82.9 (LIFT (ViT-L/14))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Generalized Few-Shot LearningonCIFAR-10-LT (ρ=10)
Error Rate· 2022-12-28
10.6
best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Generalized Few-Shot LearningonImageNet-LT
Top-1 Accuracy· 2022-12-28
53.1
best: 82.9 (LIFT (ViT-L/14))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827

Computer Vision8 results

Image ClassificationonCIFAR-10-LT (ρ=200)
Error Rate· 2022-12-28
21.9
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Few-Shot Image ClassificationoniNaturalist 2018
Top-1 Accuracy· 2022-12-28
70.1
best: 74.8 (APA (SE-ResNet-50))
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Few-Shot Image ClassificationonCIFAR-10-LT (ρ=200)
Error Rate· 2022-12-28
21.9
SOTA
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Image ClassificationonCIFAR-10-LT (ρ=10)
Error Rate· 2022-12-28
10.6
best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Image ClassificationoniNaturalist 2018
Top-1 Accuracy· 2022-12-28
70.1
best: 94.6 (OmniVec2)
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Image ClassificationonImageNet-LT
Top-1 Accuracy· 2022-12-28
53.1
best: 82.9 (LIFT (ViT-L/14))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Few-Shot Image ClassificationonCIFAR-10-LT (ρ=10)
Error Rate· 2022-12-28
10.6
best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827
Few-Shot Image ClassificationonImageNet-LT
Top-1 Accuracy· 2022-12-28
53.1
best: 82.9 (LIFT (ViT-L/14))
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data arXiv:2212.13827