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 1471–1480 of 3073 papers

TitleStatusHype
SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency—0
A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning—0
Learning with Labeling Induced Abstentions—0
Online Active Learning with Surrogate Loss Functions—0
Active Learning of Convex Halfspaces on Graphs—0
Efficient Active Learning for Gaussian Process Classification by Error Reduction—0
TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual InformationCode1
DeepAL: Deep Active Learning in PythonCode1
Improving traffic sign recognition by active searchCode0
Active Learning for Event Extraction with Memory-based Loss Prediction Model—0
Show:102550
← PrevPage 148 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