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 251–275 of 3073 papers

TitleStatusHype
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic SegmentationCode1
Reinforced active learning for image segmentationCode1
Active Learning from the WebCode1
SAAL: Sharpness-Aware Active LearningCode1
Learning Loss for Active LearningCode1
Active Learning Helps Pretrained Models Learn the Intended TaskCode1
Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite ImagesCode1
ActiveGLAE: A Benchmark for Deep Active Learning with TransformersCode1
Active Learning of Markov Decision Processes using Baum-Welch algorithm (Extended)Code1
Active Learning on a Budget: Opposite Strategies Suit High and Low BudgetsCode1
Active Learning Through a Covering LensCode1
Active Learning for Open-set AnnotationCode1
Active Learning Meets Optimized Item SelectionCode1
Active Pointly-Supervised Instance SegmentationCode1
Enhanced spatio-temporal electric load forecasts using less data with active deep learningCode1
Active learning for medical image segmentation with stochastic batchesCode1
Active Imitation Learning with Noisy GuidanceCode1
Active Statistical InferenceCode1
Active Testing: Sample-Efficient Model EvaluationCode1
Active Test-Time Adaptation: Theoretical Analyses and An AlgorithmCode1
Active Invariant Causal Prediction: Experiment Selection through StabilityCode1
D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic SegmentationCode1
Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center DatasetCode1
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacksCode1
Adaptive Superpixel for Active Learning in Semantic SegmentationCode1
Show:102550
← PrevPage 11 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