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/PEMnE-BMS*

PEMnE-BMS*

Reported on 14 benchmarks across 2 tasks · 1 paper · 12 SOTA

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

Computer Vision14 results

Image ClassificationonCUB 200 5-way 5-shot
Accuracy· uses extra data· 2021-10-18
96.43
best: 98.7 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2021-10-18
88.44
best: 89.94 (PT+MAP+SF+SOT (transductive))
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Image ClassificationonMini-ImageNet-CUB 5-way (1-shot)
Accuracy· 2021-10-18
63.9
best: 84.61 (TRIDENT)
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-10-18
86.07
best: 96.8 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-10-18
91.09
best: 98.8 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2021-10-18
91.86
best: 93.5 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Few-Shot Image ClassificationonCUB 200 5-way 5-shot
Accuracy· uses extra data· 2021-10-18
96.43
best: 98.7 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Few-Shot Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2021-10-18
88.44
best: 89.94 (PT+MAP+SF+SOT (transductive))
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Few-Shot Image ClassificationonMini-ImageNet-CUB 5-way (1-shot)
Accuracy· 2021-10-18
63.9
best: 84.61 (TRIDENT)
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Few-Shot Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-10-18
86.07
best: 96.8 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Few-Shot Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-10-18
91.09
best: 98.8 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Few-Shot Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2021-10-18
91.86
best: 93.5 (CAML [Laion-2b])
SOTA
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Image ClassificationonCUB 200 5-way 1-shot
Accuracy· uses extra data· 2021-10-18
94.78
best: 95.8 (PT+MAP+SF+SOT (transductive))
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446
Few-Shot Image ClassificationonCUB 200 5-way 1-shot
Accuracy· uses extra data· 2021-10-18
94.78
best: 95.8 (PT+MAP+SF+SOT (transductive))
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning arXiv:2110.09446