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/MCRNet-SVM

MCRNet-SVM

Reported on 12 benchmarks across 2 tasks · 1 paper

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

Computer Vision12 results

Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2020-07-21
74.7
best: 89.94 (PT+MAP+SF+SOT (transductive))
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2020-07-21
80.34
best: 98.72 (SgVA-CLIP)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2020-07-21
62.53
best: 97.95 (SgVA-CLIP)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2020-07-21
57.8
best: 70.6 (BAVARDAGE)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2020-07-21
41
best: 57.27 (BAVARDAGE)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2020-07-21
86.8
best: 93.5 (CAML [Laion-2b])
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Few-Shot Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2020-07-21
74.7
best: 89.94 (PT+MAP+SF+SOT (transductive))
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2020-07-21
80.34
best: 98.72 (SgVA-CLIP)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2020-07-21
62.53
best: 97.95 (SgVA-CLIP)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Few-Shot Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2020-07-21
57.8
best: 70.6 (BAVARDAGE)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Few-Shot Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2020-07-21
41
best: 57.27 (BAVARDAGE)
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778
Few-Shot Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2020-07-21
86.8
best: 93.5 (CAML [Laion-2b])
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach arXiv:2007.10778