Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Relation Net

Relation Net

Reported on 9 benchmarks across 2 tasks · 1 paper · 7 SOTA

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

Computer Vision9 results

Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2017-11-16
71.31
best: 98.8 (CAML [Laion-2b])
SOTA
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Image ClassificationonCUB 200 5-way 5-shot
Accuracy· 2017-11-16
65.32
best: 98.7 (CAML [Laion-2b])
SOTA
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2017-11-16
50.44
best: 95.8 (PT+MAP+SF+SOT (transductive))
SOTA
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Image ClassificationonOMNIGLOT - 1-Shot, 5-way
Accuracy· 2017-11-16
99.6
best: 99.97 (MC2+)
SOTA
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Few-Shot Image ClassificationonCUB 200 5-way 5-shot
Accuracy· 2017-11-16
65.32
best: 98.7 (CAML [Laion-2b])
SOTA
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Few-Shot Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2017-11-16
50.44
best: 95.8 (PT+MAP+SF+SOT (transductive))
SOTA
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Few-Shot Image ClassificationonOMNIGLOT - 1-Shot, 5-way
Accuracy· 2017-11-16
99.6
best: 99.97 (MC2+)
SOTA
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Image ClassificationonOMNIGLOT - 5-Shot, 5-way
Accuracy· 2017-11-16
99.8
best: 99.9 (MAML)
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025
Few-Shot Image ClassificationonOMNIGLOT - 5-Shot, 5-way
Accuracy· 2017-11-16
99.8
best: 99.9 (MAML)
Learning to Compare: Relation Network for Few-Shot Learning arXiv:1711.06025