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 2251–2260 of 3073 papers

TitleStatusHype
Active Domain Adaptation with False Negative Prediction for Object Detection—0
Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation—0
ActiveDP: Bridging Active Learning and Data Programming—0
Active emulation of computer codes with Gaussian processes -- Application to remote sensing—0
Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification—0
Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation—0
Active feature selection discovers minimal gene sets for classifying cell types and disease states with single-cell mRNA-seq data—0
Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings—0
Active Few-Shot Fine-Tuning—0
Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment—0
Show:102550
← PrevPage 226 of 308Next →

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