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 501–550 of 3073 papers

TitleStatusHype
Crowd Counting With Partial Annotations in an ImageCode0
IALE: Imitating Active Learner EnsemblesCode0
Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local FilterCode0
Active Generation for Image ClassificationCode0
ImitAL: Learned Active Learning Strategy on Synthetic DataCode0
ImitAL: Learning Active Learning Strategies from Synthetic DataCode0
Combining Data Generation and Active Learning for Low-Resource Question AnsweringCode0
Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active LearningCode0
Improving traffic sign recognition by active searchCode0
Cost-Sensitive Reference Pair Encoding for Multi-Label LearningCode0
Cost-Sensitive Active Learning for Incomplete DataCode0
Cost Effective Active SearchCode0
Cost-effective Object Detection: Active Sample Mining with Switchable Selection CriteriaCode0
covEcho Resource constrained lung ultrasound image analysis tool for faster triaging and active learningCode0
CrudeOilNews: An Annotated Crude Oil News Corpus for Event ExtractionCode0
Correlation Clustering with Adaptive Similarity QueriesCode0
Cooperative Inverse Reinforcement LearningCode0
Cost-Accuracy Aware Adaptive Labeling for Active LearningCode0
Active Learning Design: Modeling Force Output for Axisymmetric Soft Pneumatic ActuatorsCode0
Conversational Disease Diagnosis via External Planner-Controlled Large Language ModelsCode0
Cost-Effective Active Learning for Deep Image ClassificationCode0
Continual egocentric object recognitionCode0
Continual Deep Active Learning for Medical Imaging: Replay-Base Architecture for Context AdaptationCode0
Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition CharacteristicsCode0
Controllable Textual Inversion for Personalized Text-to-Image GenerationCode0
Cost-Effective Active Learning for Melanoma SegmentationCode0
Deep Active Learning with Adaptive AcquisitionCode0
Confidence Estimation Using Unlabeled DataCode0
Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular RepresentationsCode0
Confidence-Aware Active Feedback for Interactive Instance SearchCode0
Active learning in open experimental environments: selecting the right information channel(s) based on predictability in deep kernel learningCode0
Computational Job Market Analysis with Natural Language ProcessingCode0
Active Learning in Genetic Programming: Guiding Efficient Data Collection for Symbolic RegressionCode0
Computational Assessment of Hyperpartisanship in News TitlesCode0
Compute-Efficient Active LearningCode0
Constrained Multi-objective Bayesian Optimization through Optimistic Constraints EstimationCode0
Combining MixMatch and Active Learning for Better Accuracy with Fewer LabelsCode0
Active Learning-Based Species Range EstimationCode0
Committee neural network potentials control generalization errors and enable active learningCode0
Active Learning in CNNs via Expected Improvement MaximizationCode0
Active Collaborative Sensing for Energy BreakdownCode0
Comparing Active Learning Performance Driven by Gaussian Processes or Bayesian Neural Networks for Constrained Trajectory ExplorationCode0
Active learning in annotating micro-blogs dealing with e-reputationCode0
Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical GuaranteesCode0
Constraining the Parameters of High-Dimensional Models with Active LearningCode0
Characterizing the robustness of Bayesian adaptive experimental designs to active learning biasCode0
CFlowNets: Continuous Control with Generative Flow NetworksCode0
Class Balance Matters to Active Class-Incremental LearningCode0
Active Learning from Positive and Unlabeled DataCode0
CAMAL: Optimizing LSM-trees via Active LearningCode0
Show:102550
← PrevPage 11 of 62Next →

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