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/PODNet

PODNet

Reported on 9 benchmarks across 1 task · 1 paper · 8 SOTA

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

Methodology9 results

  • Incremental LearningonImageNet-100 - 50 classes + 25 steps of 2 classes
    Average Incremental Accuracy· 2020-04-28
    67.28
    best: 76.54 (RMM (ResNet-18))
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonImageNet - 500 classes + 5 steps of 100 classes
    Average Incremental Accuracy· 2020-04-28
    66.95
    best: 69.21 (RMM (ResNet-18))
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonCIFAR-100 - 50 classes + 25 steps of 2 classes
    Average Incremental Accuracy· 2020-04-28
    60.72
    best: 68.68 (D3Former)
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonCIFAR-100 - 50 classes + 50 steps of 1 class
    Average Incremental Accuracy· 2020-04-28
    57.98
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonImageNet - 500 classes + 10 steps of 50 classes
    Average Incremental Accuracy· 2020-04-28
    64.13
    best: 67.45 (RMM (ResNet-18))
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonImageNet-100 - 50 classes + 50 steps of 1 class
    Average Incremental Accuracy· 2020-04-28
    62.08
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonImageNet-100 - 50 classes + 10 steps of 5 classes
    Average Incremental Accuracy· 2020-04-28
    73.14
    best: 78.47 (RMM (ResNet-18))
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonImageNet-100 - 50 classes + 5 steps of 10 classes
    Average Incremental Accuracy· 2020-04-28
    75.82
    best: 80.22 (FOSTER)
    SOTA
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513
  • Incremental LearningonCIFAR-100-B0(5steps of 20 classes)
    Average Incremental Accuracy· 2020-04-28
    66.7
    best: 79.23 (View-Batch(TCIL))
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningarXiv:2004.13513