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/MAM (ViT-B/16)

MAM (ViT-B/16)

Reported on 11 benchmarks across 5 tasks · 1 paper · 6 SOTA

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

Methodology6 results

Generalized Few-Shot ClassificationonPlaces-LT
Top-1 Accuracy· uses extra data· 2023-04-11
51.4
best: 53.7 (LIFT (ViT-L/14))
SOTA
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Long-tail LearningonPlaces-LT
Top-1 Accuracy· uses extra data· 2023-04-11
51.4
best: 53.7 (LIFT (ViT-L/14))
SOTA
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Generalized Few-Shot LearningonPlaces-LT
Top-1 Accuracy· uses extra data· 2023-04-11
51.4
best: 53.7 (LIFT (ViT-L/14))
SOTA
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Generalized Few-Shot ClassificationonImageNet-LT
Top-1 Accuracy· uses extra data· 2023-04-11
82.3
best: 82.9 (LIFT (ViT-L/14))
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Long-tail LearningonImageNet-LT
Top-1 Accuracy· uses extra data· 2023-04-11
82.3
best: 82.9 (LIFT (ViT-L/14))
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Generalized Few-Shot LearningonImageNet-LT
Top-1 Accuracy· uses extra data· 2023-04-11
82.3
best: 82.9 (LIFT (ViT-L/14))
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173

Computer Vision5 results

Image ClassificationonWebVision-1000
Top-1 Accuracy· uses extra data· 2023-04-11
83.6
SOTA
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Image ClassificationonPlaces-LT
Top-1 Accuracy· uses extra data· 2023-04-11
51.4
best: 53.7 (LIFT (ViT-L/14))
SOTA
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Few-Shot Image ClassificationonPlaces-LT
Top-1 Accuracy· uses extra data· 2023-04-11
51.4
best: 53.7 (LIFT (ViT-L/14))
SOTA
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Image ClassificationonImageNet-LT
Top-1 Accuracy· uses extra data· 2023-04-11
82.3
best: 82.9 (LIFT (ViT-L/14))
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173
Few-Shot Image ClassificationonImageNet-LT
Top-1 Accuracy· uses extra data· 2023-04-11
82.3
best: 82.9 (LIFT (ViT-L/14))
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data arXiv:2304.05173