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/BSCD-FSL

BSCD-FSL

Reported on 24 benchmarks across 3 tasks · 1 paper · 21 SOTA

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

Methodology16 results

Few-Shot LearningonChestX
5 shot· 2019-12-16
25.97
best: 26.24 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Few-Shot LearningonPlantae
5 shot· 2019-12-16
59.27
best: 64.1 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Few-Shot Learningoncars
5 shot· 2019-12-16
52.08
best: 56.44 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Few-Shot LearningonCUB
5 shot· 2019-12-16
64.14
best: 71.59 (MSENet)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Few-Shot LearningonISIC2018
5 shot· 2019-12-16
48.11
best: 53.05 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Few-Shot LearningonPlaces
5 shot· 2019-12-16
70.06
best: 79.35 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Few-Shot LearningonCropDisease
5 shot· 2019-12-16
89.25
best: 96.51 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-LearningonChestX
5 shot· 2019-12-16
25.97
best: 26.24 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-LearningonPlantae
5 shot· 2019-12-16
59.27
best: 64.1 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-Learningoncars
5 shot· 2019-12-16
52.08
best: 56.44 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-LearningonCUB
5 shot· 2019-12-16
64.14
best: 71.59 (MSENet)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-LearningonISIC2018
5 shot· 2019-12-16
48.11
best: 53.05 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-LearningonPlaces
5 shot· 2019-12-16
70.06
best: 79.35 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-LearningonCropDisease
5 shot· 2019-12-16
89.25
best: 96.51 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Few-Shot LearningonEuroSAT
5 shot· 2019-12-16
79.08
best: 91.64 (StyleAdv-FT)
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Meta-LearningonEuroSAT
5 shot· 2019-12-16
79.08
best: 91.64 (StyleAdv-FT)
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200

Computer Vision8 results

Cross-Domain Few-ShotonChestX
5 shot· 2019-12-16
25.97
best: 26.24 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Cross-Domain Few-ShotonPlantae
5 shot· 2019-12-16
59.27
best: 64.1 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Cross-Domain Few-Shotoncars
5 shot· 2019-12-16
52.08
best: 56.44 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Cross-Domain Few-ShotonCUB
5 shot· 2019-12-16
64.14
best: 71.59 (MSENet)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Cross-Domain Few-ShotonISIC2018
5 shot· 2019-12-16
48.11
best: 53.05 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Cross-Domain Few-ShotonPlaces
5 shot· 2019-12-16
70.06
best: 79.35 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Cross-Domain Few-ShotonCropDisease
5 shot· 2019-12-16
89.25
best: 96.51 (StyleAdv-FT)
SOTA
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200
Cross-Domain Few-ShotonEuroSAT
5 shot· 2019-12-16
79.08
best: 91.64 (StyleAdv-FT)
A Broader Study of Cross-Domain Few-Shot Learning arXiv:1912.07200