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/BDCSPN

BDCSPN

Reported on 10 benchmarks across 2 tasks · 1 paper · 8 SOTA

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

Computer Vision10 results

Image ClassificationonDirichlet Mini-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2019-11-25
80.2
best: 83.6 (BAVARDAGE)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Image ClassificationonDirichlet Tiered-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2019-11-25
84.8
best: 86.6 (\alpha-TIM)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Image ClassificationonDirichlet CUB-200 (5-way, 1-shot)
1:1 Accuracy· 2019-11-25
74.5
best: 82 (BAVARDAGE)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Image ClassificationonDirichlet Tiered-Imagenet (5-way, 1-shot)
1:1 Accuracy· 2019-11-25
74.1
best: 76.6 (BAVARDAGE)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Few-Shot Image ClassificationonDirichlet Mini-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2019-11-25
80.2
best: 83.6 (BAVARDAGE)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Few-Shot Image ClassificationonDirichlet Tiered-Imagenet (5-way, 5-shot)
1:1 Accuracy· 2019-11-25
84.8
best: 86.6 (\alpha-TIM)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Few-Shot Image ClassificationonDirichlet CUB-200 (5-way, 1-shot)
1:1 Accuracy· 2019-11-25
74.5
best: 82 (BAVARDAGE)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Few-Shot Image ClassificationonDirichlet Tiered-Imagenet (5-way, 1-shot)
1:1 Accuracy· 2019-11-25
74.1
best: 76.6 (BAVARDAGE)
SOTA
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Image ClassificationonDirichlet CUB-200 (5-way, 5-shot)
1:1 Accuracy· 2019-11-25
87.1
best: 90.7 (BAVARDAGE)
Prototype Rectification for Few-Shot Learning arXiv:1911.10713
Few-Shot Image ClassificationonDirichlet CUB-200 (5-way, 5-shot)
1:1 Accuracy· 2019-11-25
87.1
best: 90.7 (BAVARDAGE)
Prototype Rectification for Few-Shot Learning arXiv:1911.10713