GLMC+MaxNorm (ResNet-32, channel x4)

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 ClassificationonCIFAR-100-LT (ρ=10)
Error Rate· 2023-05-15
25.72
best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions arXiv:2305.08661
Long-tail LearningonCIFAR-100-LT (ρ=10)
Error Rate· 2023-05-15
25.72
best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions arXiv:2305.08661
Generalized Few-Shot LearningonCIFAR-100-LT (ρ=10)
Error Rate· 2023-05-15
25.72
best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions arXiv:2305.08661

Computer Vision2 results

Image ClassificationonCIFAR-100-LT (ρ=10)
Error Rate· 2023-05-15
25.72
best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions arXiv:2305.08661
Few-Shot Image ClassificationonCIFAR-100-LT (ρ=10)
Error Rate· 2023-05-15
25.72
best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions arXiv:2305.08661