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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 171–180 of 3073 papers

Title	Date	Tasks	Status	Hype
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo	Feb 9, 2022	Active LearningImputation	CodeCode Available	1
Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets	Feb 6, 2022	Active Learning	CodeCode Available	1
PT4AL: Using Self-Supervised Pretext Tasks for Active Learning	Jan 19, 2022	Active Learningimage-classification	CodeCode Available	1
Active Learning for Open-set Annotation	Jan 18, 2022	Active Learning	CodeCode Available	1
CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials	Jan 6, 2022	Active LearningManagement	CodeCode Available	1
DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing	Jan 4, 2022	Active LearningSemantic Segmentation	CodeCode Available	1
Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training	Dec 27, 2021	3D Pose EstimationActive Learning	CodeCode Available	1
AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models	Dec 16, 2021	Active LearningLanguage Modeling	CodeCode Available	1
Towards General and Efficient Active Learning	Dec 15, 2021	Active LearningDepth Estimation	CodeCode Available	1
Active learning with MaskAL reduces annotation effort for training Mask R-CNN	Dec 13, 2021	Active Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 18 of 308Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	TypiClust	Accuracy	93.2	—	Unverified
2	PT4AL	Accuracy	93.1	—	Unverified
3	Learning loss	Accuracy	91.01	—	Unverified
4	CoreGCN	Accuracy	90.7	—	Unverified
5	Core-set	Accuracy	89.92	—	Unverified
6	Random Baseline (Resnet18)	Accuracy	88.45	—	Unverified
7	Random Baseline (VGG16)	Accuracy	85.09	—	Unverified