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 971–980 of 3073 papers

TitleStatusHype
Beyond Accuracy: ROI-driven Data Analytics of Empirical Data—0
Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification—0
Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes—0
Beyond Disagreement-based Agnostic Active Learning—0
Active Nearest-Neighbor Learning in Metric Spaces—0
Active Learning for Financial Investment Reports—0
Active Learning Approaches to Enhancing Neural Machine Translation—0
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection—0
Bias-Aware Heapified Policy for Active Learning—0
Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers—0
Show:102550
← PrevPage 98 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