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 201–225 of 3073 papers

TitleStatusHype
A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain KnowledgeCode1
Active Learning for Computationally Efficient Distribution of Binary Evolution SimulationsCode1
A comprehensive survey on deep active learning in medical image analysisCode1
All you need are a few pixels: semantic segmentation with PixelPickCode1
A Mathematical Analysis of Learning Loss for Active Learning in RegressionCode1
Fine-Tuning Language Models via Epistemic Neural NetworksCode1
Bayesian Model-Agnostic Meta-LearningCode1
Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite ImagesCode1
Generalized Category Discovery with Large Language Models in the LoopCode1
Active Learning for Coreference Resolution using Discrete AnnotationCode1
AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced DatasetsCode1
An Informative Path Planning Framework for Active Learning in UAV-based Semantic MappingCode1
Active Domain Adaptation via Clustering Uncertainty-weighted EmbeddingsCode1
GLISTER: Generalization based Data Subset Selection for Efficient and Robust LearningCode1
Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active LearningCode1
Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic SegmentationCode1
HUMAN: Hierarchical Universal Modular ANnotatorCode1
Bayesian Optimization with Conformal Prediction SetsCode1
BenchPress: A Deep Active Benchmark GeneratorCode1
Influence Selection for Active LearningCode1
Information Gain Propagation: a new way to Graph Active Learning with Soft LabelsCode1
Active Learning for Domain Adaptation: An Energy-Based ApproachCode1
Bayesian active learning for production, a systematic study and a reusable libraryCode1
ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property PredictionCode1
Bayesian Active Learning with Fully Bayesian Gaussian ProcessesCode1
Show:102550
← PrevPage 9 of 123Next →

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