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 1801–1810 of 3073 papers

TitleStatusHype
Deep Active Learning for Multi-Label Classification of Remote Sensing Images—0
Deep active learning for nonlinear system identification—0
Deep Active Learning for Object Detection with Mixture Density Networks—0
Deep Active Learning for Remote Sensing Object Detection—0
Does Deep Active Learning Work in the Wild?—0
Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradient—0
Deep Active Learning for Solvability Prediction in Power Systems—0
Deep Active Learning for Text Classification with Diverse Interpretations—0
Deep Active Learning for Video-based Person Re-identification—0
Deep Active Learning in the Open World—0
Show:102550
← PrevPage 181 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