Active Learning on CIFAR10 (10,000)

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Accuracy▼	Augmentations	Paper	Date↕	Code
1	TypiClust	93.2	No	Active Learning on a Budget: Opposite Strategies...	2022-02-06	Code
2	PT4AL	93.1	No	PT4AL: Using Self-Supervised Pretext Tasks for A...	2022-01-19	Code
3	Learning loss	91.01	No	Learning Loss for Active Learning	2019-05-09	Code
4	CoreGCN	90.7	No	Sequential Graph Convolutional Network for Activ...	2020-06-18	Code
5	Core-set	89.92	No	Active Learning for Convolutional Neural Network...	2017-08-01	Code
6	Random Baseline (Resnet18)	88.45	No	Towards Robust and Reproducible Active Learning ...	2020-02-21	Code
7	Random Baseline (VGG16)	85.09	No	Towards Robust and Reproducible Active Learning ...	2020-02-21	Code

#1TypiClustSOTA
93.2
Accuracy· 2022-02-06
Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets Code
#2PT4ALSOTA
93.1
Accuracy· 2022-01-19
PT4AL: Using Self-Supervised Pretext Tasks for Active Learning Code
#3Learning lossSOTA
91.01
Accuracy· 2019-05-09
Learning Loss for Active Learning Code
#4CoreGCN
90.7
Accuracy· 2020-06-18
Sequential Graph Convolutional Network for Active Learning Code
#5Core-setSOTA
89.92
Accuracy· 2017-08-01
Active Learning for Convolutional Neural Networks: A Core-Set Approach Code
#6Random Baseline (Resnet18)
88.45
Accuracy· 2020-02-21
Towards Robust and Reproducible Active Learning Using Neural Networks Code
#7Random Baseline (VGG16)
85.09
Accuracy· 2020-02-21
Towards Robust and Reproducible Active Learning Using Neural Networks Code