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 2276–2300 of 3073 papers

TitleStatusHype
Investigating the Effectiveness of Representations Based on Word-Embeddings in Active Learning for Labelling Text DatasetsCode0
Active Learning with Point Supervision for Cost-Effective Panicle Detection in Cereal Crops—0
Character Feature Engineering for Japanese Word Segmentation—0
ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion—0
Improving Differentially Private Models with Active Learning—0
Learning to Caption Images Through a Lifetime by Asking Questions—0
O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks—0
Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification—0
Active Anomaly Detection for time-domain discoveries—0
Data-driven discovery of free-form governing differential equations—0
Active Learning for Event Detection in Support of Disaster Analysis Applications—0
Noisy Batch Active Learning with Deterministic AnnealingCode0
Training Data Distribution Search with Ensemble Active Learning—0
Transfer Active Learning For Graph Neural Networks—0
Omnibus Dropout for Improving The Probabilistic Classification Outputs of ConvNets—0
Consistency-Based Semi-Supervised Active Learning: Towards Minimizing Labeling Budget—0
Gaussian Process Meta-Representations Of Neural Networks—0
Active Learning Graph Neural Networks via Node Feature Propagation—0
Learning in Confusion: Batch Active Learning with Noisy Oracle—0
A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain KnowledgeCode1
Sampling Bias in Deep Active Classification: An Empirical StudyCode0
Active Learning for Risk-Sensitive Inverse Reinforcement Learning—0
Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder—0
Active learning for level set estimation under cost-dependent input uncertainty—0
On weighted uncertainty sampling in active learning—0
Show:102550
← PrevPage 92 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