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/NC-FSCIL

NC-FSCIL

Reported on 12 benchmarks across 2 tasks

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

Methodology12 results

  • Continual Learningon CUB-200-2011
    Average Accuracy
    67.28
    best: 79.2 (PriViLege (ViT-L))
  • Continual Learningon CUB-200-2011
    Last Accuracy
    59.44
    best: 81.19 (CoACT)
  • Continual LearningonCIFAR-100
    Average Accuracy
    67.5
    best: 88.08 (PriViLege)
  • Continual LearningonCIFAR-100
    Last Accuracy
    56.11
    best: 86.06 (PriViLege)
  • Continual Learningonmini-Imagenet
    Average Accuracy
    67.82
    best: 95.27 (PriViLege)
  • Continual Learningonmini-Imagenet
    Last Accuracy
    58.31
    best: 96.24 (CoACT)
  • Class Incremental Learningon CUB-200-2011
    Average Accuracy
    67.28
    best: 79.2 (PriViLege (ViT-L))
  • Class Incremental Learningon CUB-200-2011
    Last Accuracy
    59.44
    best: 81.19 (CoACT)
  • Class Incremental LearningonCIFAR-100
    Average Accuracy
    67.5
    best: 88.08 (PriViLege)
  • Class Incremental LearningonCIFAR-100
    Last Accuracy
    56.11
    best: 86.06 (PriViLege)
  • Class Incremental Learningonmini-Imagenet
    Average Accuracy
    67.82
    best: 95.27 (PriViLege)
  • Class Incremental Learningonmini-Imagenet
    Last Accuracy
    58.31
    best: 96.24 (CoACT)