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/MAML

MAML

Reported on 25 benchmarks across 4 tasks · 2 papers · 16 SOTA

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

Computer Vision24 results

Image ClassificationonORBIT Clean Video Evaluation
Frame accuracy· 2021-04-08
70.58
best: 82.7 (SimpleCNAPs + LITE)
SOTA
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition arXiv:2104.03841
Few-Shot Image ClassificationonORBIT Clean Video Evaluation
Frame accuracy· 2021-04-08
70.58
best: 82.7 (SimpleCNAPs + LITE)
SOTA
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition arXiv:2104.03841
2D Pose EstimationonMP100
Mean PCK@0.2 - 1shot· 2017-03-09
61.5
best: 92.6 (CapeLLM)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonDirichlet Mini-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2017-03-09
64.5
best: 83.6 (BAVARDAGE)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonOMNIGLOT - 1-Shot, 5-way
Accuracy· 2017-03-09
98.7
best: 99.97 (MC2+)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonOMNIGLOT - 5-Shot, 5-way
Accuracy· 2017-03-09
99.9
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2017-03-09
63.1
best: 98.72 (SgVA-CLIP)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonDirichlet Mini-Imagenet (5-way, 1-shot)
1:1 Accuracy· 2017-03-09
47.6
best: 71 (BAVARDAGE)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2017-03-09
48.7
best: 97.95 (SgVA-CLIP)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonDirichlet Mini-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2017-03-09
64.5
best: 83.6 (BAVARDAGE)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonOMNIGLOT - 1-Shot, 5-way
Accuracy· 2017-03-09
98.7
best: 99.97 (MC2+)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonOMNIGLOT - 5-Shot, 5-way
Accuracy· 2017-03-09
99.9
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2017-03-09
63.1
best: 98.72 (SgVA-CLIP)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonDirichlet Mini-Imagenet (5-way, 1-shot)
1:1 Accuracy· 2017-03-09
47.6
best: 71 (BAVARDAGE)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2017-03-09
48.7
best: 97.95 (SgVA-CLIP)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2017-03-09
70.3
best: 98.8 (CAML [Laion-2b])
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonTiered ImageNet 10-way (1-shot)
Accuracy· 2017-03-09
34.4
best: 65.1 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonMini-Imagenet 10-way (5-shot)
Accuracy· 2017-03-09
46.9
best: 85.9 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonMini-Imagenet 10-way (1-shot)
Accuracy· 2017-03-09
31.3
best: 68.5 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Image ClassificationonTiered ImageNet 10-way (5-shot)
Accuracy· 2017-03-09
53.3
best: 80.6 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonTiered ImageNet 10-way (1-shot)
Accuracy· 2017-03-09
34.4
best: 65.1 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonMini-Imagenet 10-way (5-shot)
Accuracy· 2017-03-09
46.9
best: 85.9 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonMini-Imagenet 10-way (1-shot)
Accuracy· 2017-03-09
31.3
best: 68.5 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400
Few-Shot Image ClassificationonTiered ImageNet 10-way (5-shot)
Accuracy· 2017-03-09
53.3
best: 80.6 (Transductive CNAPS + FETI)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400

Methodology1 result

2D ClassificationonMP100
Mean PCK@0.2 - 1shot· 2017-03-09
61.5
best: 92.6 (CapeLLM)
SOTA
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks arXiv:1703.03400