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 1201–1225 of 3073 papers

TitleStatusHype
Active Learning Exploration of Transition Metal Complexes to Discover Method-Insensitive and Synthetically Accessible Chromophores—0
Multi-task Active Learning for Pre-trained Transformer-based ModelsCode0
Active Learning for Non-Parametric Choice Models—0
Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data—0
A Holistic Approach to Undesired Content Detection in the Real WorldCode1
Deep Surrogate of Modular Multi Pump using Active Learning—0
Image-based Detection of Surface Defects in Concrete during ConstructionCode0
Active Learning on a Programmable Photonic Quantum Processor—0
Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-LearningCode0
CTooth+: A Large-scale Dental Cone Beam Computed Tomography Dataset and Benchmark for Tooth Volume SegmentationCode1
Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic QuantitiesCode0
Information Gain Sampling for Active Learning in Medical Image Classification—0
Learning while Acquisition: Towards Active Learning Framework for Beamforming in Ultrasound Imaging—0
Deep Active Learning with Budget Annotation—0
A Survey of Learning on Small Data: Generalization, Optimization, and Challenge—0
Unsupervised Frequent Pattern Mining for CEP—0
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
Active Learning of Ordinal Embeddings: A User Study on Football Data—0
Partial-Monotone Adaptive Submodular Maximization—0
Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning—0
Active Learning Strategies for Weakly-supervised Object DetectionCode1
Efficient Classification with Counterfactual Reasoning and Active LearningCode0
Active Pointly-Supervised Instance SegmentationCode1
Stream-based active learning with linear models—0
Sample Efficient Learning of Predictors that Complement HumansCode0
Show:102550
← PrevPage 49 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