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/P>M>F (P=DINO-ViT-base, M=ProtoNet)

P>M>F (P=DINO-ViT-base, M=ProtoNet)

Reported on 10 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Computer Vision10 results

Image ClassificationonMeta-Dataset
Accuracy· 2022-04-15
84.75
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
SOTA
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· uses extra data· 2022-04-15
98.4
best: 98.72 (SgVA-CLIP)
SOTA
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· uses extra data· 2022-04-15
95.3
best: 97.95 (SgVA-CLIP)
SOTA
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Few-Shot Image ClassificationonMeta-Dataset
Accuracy· 2022-04-15
84.75
best: 85.27 (SMAT (DINO-VIT-Base-16-224))
SOTA
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· uses extra data· 2022-04-15
98.4
best: 98.72 (SgVA-CLIP)
SOTA
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· uses extra data· 2022-04-15
95.3
best: 97.95 (SgVA-CLIP)
SOTA
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· uses extra data· 2022-04-15
84.3
best: 89.94 (PT+MAP+SF+SOT (transductive))
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· uses extra data· 2022-04-15
92.2
best: 93.5 (CAML [Laion-2b])
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Few-Shot Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· uses extra data· 2022-04-15
84.3
best: 89.94 (PT+MAP+SF+SOT (transductive))
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305
Few-Shot Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· uses extra data· 2022-04-15
92.2
best: 93.5 (CAML [Laion-2b])
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference arXiv:2204.07305