TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/ELP

ELP

Reported on 26 benchmarks across 6 tasks

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

Computer Vision14 results

  • Image ClassificationonCIFAR-10-LT (ρ=10)
    Error Rate
    11.3
    best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Image ClassificationonCIFAR-100-LT (ρ=10)
    Error Rate
    40.9
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
  • Image ClassificationonCIFAR-100-LT (ρ=100)
    Error Rate
    57.6
    best: 10.9 (LPT)
  • Image ClassificationonCIFAR-10-LT (ρ=100)
    Error Rate
    22
    best: 10.42 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Image ClassificationonFGVC Aircraft
    Accuracy
    92.7
    best: 95.4 (SR-GNN)
  • Image ClassificationonStanford Cars
    Accuracy
    94.2
    best: 96.868 (efficient adaptive ensembling)
  • Image ClassificationonCUB-200-2011
    Accuracy
    88.8
    best: 92.8 (PIM)
  • Fine-Grained Image ClassificationonFGVC Aircraft
    Accuracy
    92.7
    best: 95.4 (SR-GNN)
  • Fine-Grained Image ClassificationonStanford Cars
    Accuracy
    94.2
    best: 96.1 (SR-GNN)
  • Fine-Grained Image ClassificationonCUB-200-2011
    Accuracy
    88.8
    best: 92.8 (PIM)
  • Few-Shot Image ClassificationonCIFAR-10-LT (ρ=10)
    Error Rate
    11.3
    best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Few-Shot Image ClassificationonCIFAR-100-LT (ρ=10)
    Error Rate
    40.9
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
  • Few-Shot Image ClassificationonCIFAR-100-LT (ρ=100)
    Error Rate
    57.6
    best: 10.9 (LPT)
  • Few-Shot Image ClassificationonCIFAR-10-LT (ρ=100)
    Error Rate
    22
    best: 10.42 (GLMC+MaxNorm (ResNet-34, channel x4))

Methodology12 results

  • Generalized Few-Shot ClassificationonCIFAR-10-LT (ρ=10)
    Error Rate
    11.3
    best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Generalized Few-Shot ClassificationonCIFAR-100-LT (ρ=10)
    Error Rate
    40.9
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
  • Generalized Few-Shot ClassificationonCIFAR-100-LT (ρ=100)
    Error Rate
    57.6
    best: 10.9 (LPT)
  • Generalized Few-Shot ClassificationonCIFAR-10-LT (ρ=100)
    Error Rate
    22
    best: 10.42 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Long-tail LearningonCIFAR-10-LT (ρ=10)
    Error Rate
    11.3
    best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Long-tail LearningonCIFAR-100-LT (ρ=10)
    Error Rate
    40.9
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
  • Long-tail LearningonCIFAR-100-LT (ρ=100)
    Error Rate
    57.6
    best: 10.9 (LPT)
  • Long-tail LearningonCIFAR-10-LT (ρ=100)
    Error Rate
    22
    best: 10.42 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Generalized Few-Shot LearningonCIFAR-10-LT (ρ=10)
    Error Rate
    11.3
    best: 5 (GLMC+MaxNorm (ResNet-34, channel x4))
  • Generalized Few-Shot LearningonCIFAR-100-LT (ρ=10)
    Error Rate
    40.9
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
  • Generalized Few-Shot LearningonCIFAR-100-LT (ρ=100)
    Error Rate
    57.6
    best: 10.9 (LPT)
  • Generalized Few-Shot LearningonCIFAR-10-LT (ρ=100)
    Error Rate
    22
    best: 10.42 (GLMC+MaxNorm (ResNet-34, channel x4))