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 226–250 of 3073 papers

TitleStatusHype
LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active LearningCode1
Active WeaSuL: Improving Weak Supervision with Active LearningCode1
Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active LearningCode1
Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?Code1
A Mathematical Analysis of Learning Loss for Active Learning in RegressionCode1
On the Importance of Effectively Adapting Pretrained Language Models for Active LearningCode1
Can Active Learning Preemptively Mitigate Fairness Issues?Code1
Model Learning with Personalized Interpretability Estimation (ML-PIE)Code1
All you need are a few pixels: semantic segmentation with PixelPickCode1
Deep Indexed Active Learning for Matching Heterogeneous Entity RepresentationsCode1
Multiple instance active learning for object detectionCode1
Is segmentation uncertainty useful?Code1
Active Learning for Deep Object Detection via Probabilistic ModelingCode1
Consistency-based Active Learning for Object DetectionCode1
Active Testing: Sample-Efficient Model EvaluationCode1
Discrepancy-Based Active Learning for Domain AdaptationCode1
Active learning based generative design for the discovery of wide bandgap materialsCode1
Deep Deterministic Uncertainty: A Simple BaselineCode1
SISE-PC: Semi-supervised Image Subsampling for Explainable PathologyCode1
DEUP: Direct Epistemic Uncertainty PredictionCode1
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacksCode1
Towards Understanding the Behaviors of Optimal Deep Active Learning AlgorithmsCode1
GLISTER: Generalization based Data Subset Selection for Efficient and Robust LearningCode1
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert LinkingCode1
Accelerating high-throughput virtual screening through molecular pool-based active learningCode1
Show:102550
← PrevPage 10 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