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/Invariance-Equivariance

Invariance-Equivariance

Reported on 18 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 Vision18 results

Image ClassificationonMeta-Dataset
Accuracy· 2021-03-01
68.89
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2021-03-01
77.87
best: 89.94 (PT+MAP+SF+SOT (transductive))
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2021-03-01
84.78
best: 98.72 (SgVA-CLIP)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-03-01
67.28
best: 97.95 (SgVA-CLIP)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2021-03-01
65.3
best: 70.6 (BAVARDAGE)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2021-03-01
47.76
best: 57.27 (BAVARDAGE)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-03-01
72.21
best: 96.8 (CAML [Laion-2b])
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-03-01
87.08
best: 98.8 (CAML [Laion-2b])
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2021-03-01
89.74
best: 93.5 (CAML [Laion-2b])
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonMeta-Dataset
Accuracy· 2021-03-01
68.89
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2021-03-01
77.87
best: 89.94 (PT+MAP+SF+SOT (transductive))
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2021-03-01
84.78
best: 98.72 (SgVA-CLIP)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-03-01
67.28
best: 97.95 (SgVA-CLIP)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2021-03-01
65.3
best: 70.6 (BAVARDAGE)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2021-03-01
47.76
best: 57.27 (BAVARDAGE)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-03-01
72.21
best: 96.8 (CAML [Laion-2b])
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-03-01
87.08
best: 98.8 (CAML [Laion-2b])
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315
Few-Shot Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2021-03-01
89.74
best: 93.5 (CAML [Laion-2b])
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning arXiv:2103.01315