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 2381–2390 of 3073 papers

TitleStatusHype
Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling—0
Markerless Multi-view 3D Human Pose Estimation: a survey—0
Mask-guided sample selection for Semi-Supervised Instance Segmentation—0
Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning—0
MAViC: Multimodal Active Learning for Video Captioning—0
Maximally Separated Active Learning—0
Maximizing Information Gain in Privacy-Aware Active Learning of Email Anomalies—0
A Unified Batch Selection Policy for Active Metric Learning—0
MEAL: Manifold Embedding-based Active Learning—0
Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detection—0
Show:102550
← PrevPage 239 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