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/RMM (ResNet-18)

RMM (ResNet-18)

Reported on 8 benchmarks across 1 task · 1 paper · 5 SOTA

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

Methodology8 results

  • Incremental LearningonImageNet-100 - 50 classes + 25 steps of 2 classes
    Average Incremental Accuracy· 2023-01-14
    76.54
    SOTA
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792
  • Incremental LearningonImageNet - 500 classes + 5 steps of 100 classes
    Average Incremental Accuracy· 2023-01-14
    69.21
    SOTA
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792
  • Incremental LearningonImageNet - 500 classes + 25 steps of 20 classes
    Average Incremental Accuracy· 2023-01-14
    63.93
    SOTA
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792
  • Incremental LearningonImageNet - 500 classes + 10 steps of 50 classes
    Average Incremental Accuracy· 2023-01-14
    67.45
    SOTA
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792
  • Incremental LearningonImageNet-100 - 50 classes + 10 steps of 5 classes
    Average Incremental Accuracy· 2023-01-14
    78.47
    SOTA
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792
  • Incremental LearningonImageNet - 10 steps
    Average Incremental Accuracy· 2023-01-14
    67.45
    best: 85.5 (kNN-CLIP)
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792
  • Incremental LearningonImageNet100 - 10 steps
    Average Incremental Accuracy· 2023-01-14
    78.47
    best: 85.1 (kNN-CLIP)
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792
  • Incremental LearningonImageNet-100 - 50 classes + 5 steps of 10 classes
    Average Incremental Accuracy· 2023-01-14
    79.52
    best: 80.22 (FOSTER)
    RMM: Reinforced Memory Management for Class-Incremental LearningarXiv:2301.05792