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 91–100 of 3073 papers

TitleStatusHype
A2-LINK: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain KnowledgeCode1
Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite ImagesCode1
Active Transfer Learning for Efficient Video-Specific Human Pose EstimationCode1
AL-GTD: Deep Active Learning for Gaze Target DetectionCode1
Active Learning Through a Covering LensCode1
An Informative Path Planning Framework for Active Learning in UAV-based Semantic MappingCode1
Active Learning for Open-set AnnotationCode1
Active Learning for Optimal Intervention Design in Causal ModelsCode1
A Simple Baseline for Low-Budget Active LearningCode1
Active Anomaly Detection via EnsemblesCode1
Show:102550
← PrevPage 10 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