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/Piggyback

Piggyback

Reported on 8 benchmarks across 1 task · 1 paper · 4 SOTA

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

Methodology8 results

  • Continual LearningonSketch (Fine-grained 6 Tasks)
    Accuracy· 2018-01-19
    79.91
    best: 80.77 (CondConvContinual)
    SOTA
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519
  • Continual LearningonStanford Cars (Fine-grained 6 Tasks)
    Accuracy· 2018-01-19
    89.62
    best: 92.8 (CPG)
    SOTA
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519
  • Continual LearningonCUBS (Fine-grained 6 Tasks)
    Accuracy· 2018-01-19
    80.5
    best: 84.26 (CondConvContinual)
    SOTA
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519
  • Continual LearningonFlowers (Fine-grained 6 Tasks)
    Accuracy· 2018-01-19
    94.77
    best: 97.16 (CondConvContinual)
    SOTA
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519
  • Continual Learningonvisual domain decathlon (10 tasks)
    Avg. Accuracy· 2018-01-19
    76.6
    best: 79.64 (NetTailor)
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519
  • Continual Learningonvisual domain decathlon (10 tasks)
    decathlon discipline (Score)· 2018-01-19
    2838
    best: 3744 (NetTailor)
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519
  • Continual LearningonWikiart (Fine-grained 6 Tasks)
    Accuracy· 2018-01-19
    71.33
    best: 78.32 (CondConvContinual)
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519
  • Continual LearningonImageNet (Fine-grained 6 Tasks)
    Accuracy· 2018-01-19
    76.16
    Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsarXiv:1801.06519