SOTAVerified

Active Learning

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2411–2420 of 3073 papers

TitleStatusHype
MILAN: Milli-Annotations for Lidar Semantic Segmentation—0
Minimax Active Learning—0
Minimax Analysis of Active Learning—0
Minimizing Supervision in Multi-label Categorization—0
Supporting Land Reuse of Former Open Pit Mining Sites using Text Classification and Active Learning—0
Mining Object Parts from CNNs via Active Question-Answering—0
Mining of Single-Class by Active Learning for Semantic Segmentation—0
Mining Unstructured Medical Texts With Conformal Active Learning—0
Minority Class Oriented Active Learning for Imbalanced Datasets—0
Mitigating Sampling Bias and Improving Robustness in Active Learning—0
Show:102550
← PrevPage 242 of 308Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TypiClustAccuracy93.2—Unverified
2PT4ALAccuracy93.1—Unverified
3Learning lossAccuracy91.01—Unverified
4CoreGCNAccuracy90.7—Unverified
5Core-setAccuracy89.92—Unverified
6Random Baseline (Resnet18)Accuracy88.45—Unverified
7Random Baseline (VGG16)Accuracy85.09—Unverified