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/Multi-Task Learning

Multi-Task Learning

Reported on 16 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 Vision16 results

Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2021-06-16
69.5
best: 89.94 (PT+MAP+SF+SOT (transductive))
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2021-06-16
77.72
best: 98.72 (SgVA-CLIP)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-06-16
59.84
best: 97.95 (SgVA-CLIP)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2021-06-16
57.7
best: 70.6 (BAVARDAGE)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2021-06-16
42.4
best: 57.27 (BAVARDAGE)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-06-16
67.11
best: 96.8 (CAML [Laion-2b])
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-06-16
83.69
best: 98.8 (CAML [Laion-2b])
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2021-06-16
84.1
best: 93.5 (CAML [Laion-2b])
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonCIFAR-FS 5-way (1-shot)
Accuracy· 2021-06-16
69.5
best: 89.94 (PT+MAP+SF+SOT (transductive))
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2021-06-16
77.72
best: 98.72 (SgVA-CLIP)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-06-16
59.84
best: 97.95 (SgVA-CLIP)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonFC100 5-way (5-shot)
Accuracy· 2021-06-16
57.7
best: 70.6 (BAVARDAGE)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonFC100 5-way (1-shot)
Accuracy· 2021-06-16
42.4
best: 57.27 (BAVARDAGE)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-06-16
67.11
best: 96.8 (CAML [Laion-2b])
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-06-16
83.69
best: 98.8 (CAML [Laion-2b])
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017
Few-Shot Image ClassificationonCIFAR-FS 5-way (5-shot)
Accuracy· 2021-06-16
84.1
best: 93.5 (CAML [Laion-2b])
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation arXiv:2106.09017