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/DER

DER

Reported on 9 benchmarks across 1 task · 1 paper · 2 SOTA

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

Methodology9 results

  • Incremental LearningonImageNet100 - 10 steps
    Final Accuracy Top-5· 2021-03-31
    88.38
    best: 88.84 (TCIL)
    SOTA
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet-100 - 50 classes + 10 steps of 5 classes
    Average Incremental Accuracy· 2021-03-31
    77.73
    best: 78.47 (RMM (ResNet-18))
    SOTA
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet - 10 steps
    Average Incremental Accuracy· 2021-03-31
    66.73
    best: 85.5 (kNN-CLIP)
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet - 10 steps
    Average Incremental Accuracy Top-5· 2021-03-31
    87.08
    best: 88.59 (DyTox)
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet - 10 steps
    Final Accuracy· 2021-03-31
    58.62
    best: 63.34 (DyTox)
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet - 10 steps
    Final Accuracy Top-5· 2021-03-31
    81.89
    best: 84.49 (DyTox)
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet100 - 10 steps
    Average Incremental Accuracy· 2021-03-31
    76.12
    best: 85.1 (kNN-CLIP)
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet100 - 10 steps
    Average Incremental Accuracy Top-5· 2021-03-31
    92.79
    best: 94.17 (TCIL)
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788
  • Incremental LearningonImageNet100 - 10 steps
    Final Accuracy· 2021-03-31
    66.07
    best: 69.1 (DyTox)
    DER: Dynamically Expandable Representation for Class Incremental LearningarXiv:2103.16788