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/Delta-encoder

Delta-encoder

Reported on 8 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision8 results

  • Image ClassificationonCUB 200 5-way 1-shot
    Accuracy· 2018-06-12
    69.8
    best: 95.8 (PT+MAP+SF+SOT (transductive))
    SOTA
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734
  • Image ClassificationonMini-Imagenet 5-way (1-shot)
    Accuracy· 2018-06-12
    59.9
    best: 97.95 (SgVA-CLIP)
    SOTA
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734
  • Few-Shot Image ClassificationonCUB 200 5-way 1-shot
    Accuracy· 2018-06-12
    69.8
    best: 95.8 (PT+MAP+SF+SOT (transductive))
    SOTA
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734
  • Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
    Accuracy· 2018-06-12
    59.9
    best: 97.95 (SgVA-CLIP)
    SOTA
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734
  • Image ClassificationonCIFAR100 5-way (1-shot)
    Accuracy· 2018-06-12
    66.7
    best: 89.6 (UL-Hopfield (ULH))
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734
  • Image ClassificationonCaltech-256 5-way (1-shot)
    Accuracy· 2018-06-12
    73.2
    best: 74.7 (UL-Hopfield (ULH))
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734
  • Few-Shot Image ClassificationonCIFAR100 5-way (1-shot)
    Accuracy· 2018-06-12
    66.7
    best: 89.6 (UL-Hopfield (ULH))
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734
  • Few-Shot Image ClassificationonCaltech-256 5-way (1-shot)
    Accuracy· 2018-06-12
    73.2
    best: 74.7 (UL-Hopfield (ULH))
    Delta-encoder: an effective sample synthesis method for few-shot object recognitionarXiv:1806.04734