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 791–800 of 3073 papers

TitleStatusHype
Learning Formal Specifications from Membership and Preference Queries—0
Active learning of effective Hamiltonian for super-large-scale atomic structures—0
Mining of Single-Class by Active Learning for Semantic Segmentation—0
Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning—0
Active Learning for Object Detection with Non-Redundant Informative Sampling—0
Recognition of Mental Adjectives in An Efficient and Automatic Style—0
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection—0
Defect Classification in Additive Manufacturing Using CNN-Based Vision Processing—0
Exploiting Counter-Examples for Active Learning with Partial labelsCode0
Adaptive Region Selection for Active Learning in Whole Slide Image Semantic SegmentationCode0
Show:102550
← PrevPage 80 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