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 1001–1025 of 3073 papers

TitleStatusHype
Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance AssessmentCode1
HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling—0
Cross-lingual German Biomedical Information Extraction: from Zero-shot to Human-in-the-Loop—0
Semi-Automated Construction of Food Composition Knowledge BaseCode0
Exploring Active 3D Object Detection from a Generalization PerspectiveCode1
Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning—0
Active Learning of Piecewise Gaussian Process Surrogates—0
Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement PrioritizationCode0
Active learning for medical image segmentation with stochastic batchesCode1
Computational Assessment of Hyperpartisanship in News TitlesCode0
TAAL: Test-time Augmentation for Active Learning in Medical Image SegmentationCode0
Scalable Batch Acquisition for Deep Bayesian Active LearningCode0
Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data—0
Combining Self-labeling with Selective Sampling—0
A domain-decomposed VAE method for Bayesian inverse problems—0
Active Learning for Abstractive Text SummarizationCode0
How to Allocate your Label Budget? Choosing between Active Learning and Learning to Reject in Anomaly DetectionCode0
Active Learning Guided by Efficient Surrogate Learners—0
Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space—0
An interpretable machine learning system for colorectal cancer diagnosis from pathology slides—0
MoBYv2AL: Self-supervised Active Learning for Image ClassificationCode1
Benchmarks and Algorithms for Offline Preference-Based Reward Learning—0
Using Active Learning Methods to Strategically Select Essays for Automated Scoring—0
Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking—0
Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active LearningCode1
Show:102550
← PrevPage 41 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