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 101–150 of 3073 papers

TitleStatusHype
A comprehensive survey on deep active learning in medical image analysisCode1
Causal-Guided Active Learning for Debiasing Large Language ModelsCode1
Class-Balanced Active Learning for Image ClassificationCode1
Closing the Loop: Fast, Interactive Semi-Supervised Annotation With Queries on Features and InstancesCode1
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert LinkingCode1
Active Domain Adaptation via Clustering Uncertainty-weighted EmbeddingsCode1
COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image SegmentationCode1
Conditioning Sparse Variational Gaussian Processes for Online Decision-makingCode1
Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)Code1
Consistency-based Active Learning for Object DetectionCode1
Adaptive Superpixel for Active Learning in Semantic SegmentationCode1
Active Learning by Feature MixingCode1
Active Learning by Acquiring Contrastive ExamplesCode1
CriticLean: Critic-Guided Reinforcement Learning for Mathematical FormalizationCode1
Data-Driven Autoencoder Numerical Solver with Uncertainty Quantification for Fast Physical SimulationsCode1
Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regressionCode1
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacksCode1
DEAL: Deep Evidential Active Learning for Image ClassificationCode1
A Benchmark on Uncertainty Quantification for Deep Learning PrognosticsCode1
Deep Active Learning for Biased Datasets via Fisher Kernel Self-SupervisionCode1
Deep Active Learning for Named Entity RecognitionCode1
Deep Active Learning in Remote Sensing for data efficient Change DetectionCode1
Active Transfer Learning for Efficient Video-Specific Human Pose EstimationCode1
Active Test-Time Adaptation: Theoretical Analyses and An AlgorithmCode1
DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the LoopCode1
Active WeaSuL: Improving Weak Supervision with Active LearningCode1
Active Sensing for Communications by LearningCode1
Accelerating high-throughput virtual screening through molecular pool-based active learningCode1
Active Statistical InferenceCode1
AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language ModelsCode1
A dynamic Bayesian optimized active recommender system for curiosity-driven Human-in-the-loop automated experimentsCode1
Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-TrainingCode1
Active Learning Strategies for Weakly-supervised Object DetectionCode1
Enhanced spatio-temporal electric load forecasts using less data with active deep learningCode1
Active Learning Meets Optimized Item SelectionCode1
Active Learning Helps Pretrained Models Learn the Intended TaskCode1
Active Learning of Markov Decision Processes using Baum-Welch algorithm (Extended)Code1
Active Learning for Optimal Intervention Design in Causal ModelsCode1
Active Invariant Causal Prediction: Experiment Selection through StabilityCode1
Active Learning Through a Covering LensCode1
Active Learning from the WebCode1
Active learning with MaskAL reduces annotation effort for training Mask R-CNNCode1
Active Learning on a Budget: Opposite Strategies Suit High and Low BudgetsCode1
ActiveNeRF: Learning where to See with Uncertainty EstimationCode1
Active Prompt Learning in Vision Language ModelsCode1
Active Learning for Domain Adaptation: An Energy-Based ApproachCode1
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model EvaluationCode1
Active Testing: Sample-Efficient Model EvaluationCode1
Active Anomaly Detection via EnsemblesCode1
Active Imitation Learning with Noisy GuidanceCode1
Show:102550
← PrevPage 3 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