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 151–175 of 3073 papers

TitleStatusHype
Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active LearningCode1
Active Learning from the WebCode1
Active Bayesian Causal InferenceCode1
Building a Scalable and Interpretable Bayesian Deep Learning Framework for Quality Control of Free Form SurfacesCode1
Active Learning Helps Pretrained Models Learn the Intended TaskCode1
Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational DataCode1
Active Learning for Convolutional Neural Networks: A Core-Set ApproachCode1
Active Learning at the ImageNet ScaleCode1
Active Learning Strategies for Weakly-supervised Object DetectionCode1
CloudS2Mask: A novel deep learning approach for improved cloud and cloud shadow masking in Sentinel-2 imageryCode1
Active Learning on a Budget: Opposite Strategies Suit High and Low BudgetsCode1
Active learning based generative design for the discovery of wide bandgap materialsCode1
Active Learning Through a Covering LensCode1
COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image SegmentationCode1
Confidence-Aware Learning for Deep Neural NetworksCode1
Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)Code1
Active Imitation Learning with Noisy GuidanceCode1
Active Learning for Coreference Resolution using Discrete AnnotationCode1
Counting People by Estimating People FlowsCode1
Creating Custom Event Data Without Dictionaries: A Bag-of-TricksCode1
Active Learning by Acquiring Contrastive ExamplesCode1
Active Learning by Feature MixingCode1
Unsupervised Selective Labeling for More Effective Semi-Supervised LearningCode1
Data-Driven Autoencoder Numerical Solver with Uncertainty Quantification for Fast Physical SimulationsCode1
Active Learning for Computationally Efficient Distribution of Binary Evolution SimulationsCode1
Show:102550
← PrevPage 7 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