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 201–250 of 3073 papers

TitleStatusHype
All you need are a few pixels: semantic segmentation with PixelPickCode1
Active Learning for Computationally Efficient Distribution of Binary Evolution SimulationsCode1
A comprehensive survey on deep active learning in medical image analysisCode1
A Mathematical Analysis of Learning Loss for Active Learning in RegressionCode1
Fine-Tuning Language Models via Epistemic Neural NetworksCode1
Fink: early supernovae Ia classification using active learningCode1
Active Learning for Optimal Intervention Design in Causal ModelsCode1
GeneDisco: A Benchmark for Experimental Design in Drug DiscoveryCode1
AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced DatasetsCode1
Active Learning for Coreference Resolution using Discrete AnnotationCode1
GFlowNet FoundationsCode1
An Informative Path Planning Framework for Active Learning in UAV-based Semantic MappingCode1
Active Domain Adaptation via Clustering Uncertainty-weighted EmbeddingsCode1
Gone Fishing: Neural Active Learning with Fisher EmbeddingsCode1
Bayesian Model-Agnostic Meta-LearningCode1
On the Importance of Effectively Adapting Pretrained Language Models for Active LearningCode1
ICS: Total Freedom in Manual Text Classification Supported by Unobtrusive Machine LearningCode1
Inconsistency-Based Data-Centric Active Open-Set AnnotationCode1
Bayesian Optimization with Conformal Prediction SetsCode1
Information Gain Propagation: a new way to Graph Active Learning with Soft LabelsCode1
Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active LearningCode1
infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-informationCode1
Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science DomainsCode1
AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African LanguagesCode1
Knowledge-Aware Federated Active Learning with Non-IID DataCode1
What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical PerspectiveCode1
Open Source Software for Efficient and Transparent ReviewsCode1
LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active LearningCode1
Active Learning for Domain Adaptation: An Energy-Based ApproachCode1
AstronomicAL: An interactive dashboard for visualisation, integration and classification of data using Active LearningCode1
LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic SegmentationCode1
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled SamplesCode1
LTP: A New Active Learning Strategy for CRF-Based Named Entity RecognitionCode1
A Survey of Dataset Refinement for Problems in Computer Vision DatasetsCode1
AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language ModelsCode1
A unified framework for closed-form nonparametric regression, classification, preference and mixed problems with Skew Gaussian ProcessesCode1
A Tutorial on Thompson SamplingCode1
Making Your First Choice: To Address Cold Start Problem in Vision Active LearningCode1
A Benchmark on Uncertainty Quantification for Deep Learning PrognosticsCode1
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyCode1
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte CarloCode1
MoBYv2AL: Self-supervised Active Learning for Image ClassificationCode1
Model Learning with Personalized Interpretability Estimation (ML-PIE)Code1
Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite ImagesCode1
Bayesian active learning for production, a systematic study and a reusable libraryCode1
Multi-Objective GFlowNetsCode1
Learning Loss for Active LearningCode1
Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance AssessmentCode1
ActiveGLAE: A Benchmark for Deep Active Learning with TransformersCode1
Active learning for medical image segmentation with stochastic batchesCode1
Show:102550
← PrevPage 5 of 62Next →

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