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 51–75 of 3073 papers

TitleStatusHype
Active Learning for Convolutional Neural Networks: A Core-Set ApproachCode1
Active Learning for Coreference Resolution using Discrete AnnotationCode1
D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic SegmentationCode1
A deep active learning system for species identification and counting in camera trap imagesCode1
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model EvaluationCode1
A Framework and Benchmark for Deep Batch Active Learning for RegressionCode1
Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation EffortsCode1
Active Learning for Domain Adaptation: An Energy-Based ApproachCode1
A Comparative Survey of Deep Active LearningCode1
Active learning for medical image segmentation with stochastic batchesCode1
AL-GTD: Deep Active Learning for Gaze Target DetectionCode1
Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite ImagesCode1
Active Learning by Acquiring Contrastive ExamplesCode1
Active Testing: Sample-Efficient Model EvaluationCode1
Active Learning at the ImageNet ScaleCode1
Active learning based generative design for the discovery of wide bandgap materialsCode1
Active Prompt Learning in Vision Language ModelsCode1
Active Sensing for Communications by LearningCode1
Active Statistical InferenceCode1
Active Test-Time Adaptation: Theoretical Analyses and An AlgorithmCode1
Active Invariant Causal Prediction: Experiment Selection through StabilityCode1
Enhanced spatio-temporal electric load forecasts using less data with active deep learningCode1
ActiveNeRF: Learning where to See with Uncertainty EstimationCode1
Active Anomaly Detection via EnsemblesCode1
Active learning with MaskAL reduces annotation effort for training Mask R-CNNCode1
Show:102550
← PrevPage 3 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