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/pseudo-shots

pseudo-shots

Reported on 18 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision18 results

Image ClassificationonCIFAR-FS - 5-Shot Learning
Accuracy· 2020-12-13
89.12
SOTA
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonCIFAR-FS - 5-Shot Learning
Accuracy· 2020-12-13
89.12
SOTA
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2020-12-13
81.87
best: 89.94 (PT+MAP+SF+SOT (transductive))
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2020-12-13
82.51
best: 98.72 (SgVA-CLIP)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2020-12-13
73.35
best: 97.95 (SgVA-CLIP)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2020-12-13
61.58
best: 70.6 (BAVARDAGE)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2020-12-13
50.57
best: 57.27 (BAVARDAGE)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2020-12-13
76.55
best: 96.8 (CAML [Laion-2b])
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2020-12-13
86.82
best: 98.8 (CAML [Laion-2b])
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2020-12-13
89.12
best: 93.5 (CAML [Laion-2b])
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2020-12-13
81.87
best: 89.94 (PT+MAP+SF+SOT (transductive))
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2020-12-13
82.51
best: 98.72 (SgVA-CLIP)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2020-12-13
73.35
best: 97.95 (SgVA-CLIP)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2020-12-13
61.58
best: 70.6 (BAVARDAGE)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2020-12-13
50.57
best: 57.27 (BAVARDAGE)
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2020-12-13
76.55
best: 96.8 (CAML [Laion-2b])
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2020-12-13
86.82
best: 98.8 (CAML [Laion-2b])
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176
Few-Shot Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2020-12-13
89.12
best: 93.5 (CAML [Laion-2b])
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks arXiv:2012.07176