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 251–300 of 3073 papers

TitleStatusHype
CitySurfaces: City-Scale Semantic Segmentation of Sidewalk MaterialsCode1
CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic OutputCode1
Class-Balanced Active Learning for Image ClassificationCode1
Towards Balanced Active Learning for Multimodal ClassificationCode1
Active Learning from the WebCode1
Consistency-based Active Learning for Object DetectionCode1
Confidence-Aware Learning for Deep Neural NetworksCode1
Conditioning Sparse Variational Gaussian Processes for Online Decision-makingCode1
Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)Code1
Contextual Diversity for Active LearningCode1
Stochastic Batch Acquisition: A Simple Baseline for Deep Active LearningCode1
Active Learning Helps Pretrained Models Learn the Intended TaskCode1
Active Learning Meets Optimized Item SelectionCode1
Counting People by Estimating People FlowsCode1
Active Learning of Markov Decision Processes using Baum-Welch algorithm (Extended)Code1
Active learning for medical image segmentation with stochastic batchesCode1
Active Imitation Learning with Noisy GuidanceCode1
Active Learning on a Budget: Opposite Strategies Suit High and Low BudgetsCode1
Active Learning Through a Covering LensCode1
Active Learning Strategies for Weakly-supervised Object DetectionCode1
Active Invariant Causal Prediction: Experiment Selection through StabilityCode1
Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-TrainingCode1
Learning Loss for Active LearningCode1
DEAL: Deep Evidential Active Learning for Image ClassificationCode1
Cold-start Active Learning through Self-supervised Language ModelingCode1
Deep Active Learning for Axon-Myelin Segmentation on Histology DataCode1
Active learning with MaskAL reduces annotation effort for training Mask R-CNNCode1
Deep Active Learning for Joint Classification & Segmentation with Weak AnnotatorCode1
Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite ImagesCode1
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower BoundsCode1
DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the LoopCode1
ActiveGLAE: A Benchmark for Deep Active Learning with TransformersCode1
Active Pointly-Supervised Instance SegmentationCode1
Deep Deterministic Uncertainty: A Simple BaselineCode1
Enhanced spatio-temporal electric load forecasts using less data with active deep learningCode1
Active Learning for Open-set AnnotationCode1
COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image SegmentationCode1
Accelerating high-throughput virtual screening through molecular pool-based active learningCode1
Active Prompt Learning in Vision Language ModelsCode1
Continuous Learning for Android Malware DetectionCode1
Dataset Quantization with Active Learning based Adaptive SamplingCode1
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple HumansCode1
Diversify and Conquer: Diversity-Centric Data Selection with Iterative RefinementCode1
Active Sensing for Communications by LearningCode1
Entropic Open-set Active LearningCode1
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model EvaluationCode1
Active Test-Time Adaptation: Theoretical Analyses and An AlgorithmCode1
Active Testing: Sample-Efficient Model EvaluationCode1
Active Anomaly Detection via EnsemblesCode1
Fink: early supernovae Ia classification using active learningCode1
Show:102550
← PrevPage 6 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