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 1451–1500 of 3073 papers

TitleStatusHype
Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-TrainingCode1
Unsupervised Clustering Active Learning for Person Re-identification—0
On the relationship between calibrated predictors and unbiased volume estimationCode0
Fair Active Learning: Solving the Labeling Problem in Insurance—0
AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language ModelsCode1
Curriculum learning for data-driven modeling of dynamical systems—0
Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort—0
Towards General and Efficient Active LearningCode1
LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework—0
Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not—0
Active learning with MaskAL reduces annotation effort for training Mask R-CNNCode1
Depth Uncertainty Networks for Active Learning—0
Gamifying optimization: a Wasserstein distance-based analysis of human search—0
CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation—0
Boosting Active Learning via Improving Test PerformanceCode1
Active Sensing for Communications by LearningCode1
Multi-View Active Learning for Short Text Classification in User-Generated Data—0
Robust Active Learning: Sample-Efficient Training of Robust Deep Learning Models—0
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled SamplesCode1
Active Learning for Domain Adaptation: An Energy-Based ApproachCode1
SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency—0
A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning—0
Active Learning of Convex Halfspaces on Graphs—0
Efficient Active Learning for Gaussian Process Classification by Error Reduction—0
Learning with Labeling Induced Abstentions—0
Online Active Learning with Surrogate Loss Functions—0
TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual InformationCode1
DeepAL: Deep Active Learning in PythonCode1
Improving traffic sign recognition by active searchCode0
Active Learning for Event Extraction with Memory-based Loss Prediction Model—0
Active Learning at the ImageNet ScaleCode1
Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition CharacteristicsCode0
Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic SegmentationCode1
Active Learning Meets Optimized Item SelectionCode1
Fink: early supernovae Ia classification using active learningCode1
Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation—0
YMIR: A Rapid Data-centric Development Platform for Vision ApplicationsCode1
Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification—0
GFlowNet FoundationsCode1
Probing Difficulty and Discrimination of Natural Language Questions With Item Response Theory—0
Towards Computationally Feasible Deep Active Learning—0
Active Relation Discovery: Towards General and Label-aware OpenRE—0
Active Dialogue Simulation in Conversational Systems—0
Cost-Effective Training in Low-Resource Neural Machine Translation—0
Single Image Object Counting and Localizing using Active-Learning—0
Code-free development and deployment of deep segmentation models for digital pathologyCode1
Reducing the Long Tail Losses in Scientific Emulations with Active LearningCode0
Adding more data does not always help: A study in medical conversation summarization with PEGASUS—0
Solving Multi-Arm Bandit Using a Few Bits of Communication—0
A Histopathology Study Comparing Contrastive Semi-Supervised and Fully Supervised Learning—0
Show:102550
← PrevPage 30 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