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 1576–1600 of 3073 papers

TitleStatusHype
The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning—0
The CAMOMILE Collaborative Annotation Platform for Multi-modal, Multi-lingual and Multi-media Documents—0
The Cost of Replicability in Active Learning—0
The Effectiveness of Variational Autoencoders for Active Learning—0
Bayesian Active Learning in the Presence of Nuisance Parameters—0
The Impact of Typicality for Informative Representative Selection—0
The Importance of Metric Learning for Robotic Vision: Open Set Recognition and Active Learning—0
The Infinite Index: Information Retrieval on Generative Text-To-Image Models—0
The Power of Comparisons for Actively Learning Linear Classifiers—0
The Power of Ensembles for Active Learning in Image Classification—0
The Power of Localization for Efficiently Learning Linear Separators with Noise—0
The Practical Challenges of Active Learning: Lessons Learned from Live Experimentation—0
The Relationship Between Agnostic Selective Classification Active Learning and the Disagreement Coefficient—0
The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning—0
The Role of Higher-Order Cognitive Models in Active Learning—0
The Search for Squawk: Agile Modeling in Bioacoustics—0
The Solution Path Algorithm for Identity-Aware Multi-Object Tracking—0
The trade-off between data minimization and fairness in collaborative filtering—0
The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation—0
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes—0
The Use of AI-Robotic Systems for Scientific Discovery—0
The Use of Unlabeled Data versus Labeled Data for Stopping Active Learning for Text Classification—0
The Utility of Abstaining in Binary Classification—0
The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration—0
The Work Capacity of Channels with Memory: Maximum Extractable Work in Percept-Action Loops—0
Show:102550
← PrevPage 64 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