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 1951–1975 of 3073 papers

TitleStatusHype
Robot Design With Neural Networks, MILP Solvers and Active Learning—0
Semi-supervised Batch Active Learning via Bilevel OptimizationCode1
Cold-start Active Learning through Self-supervised Language ModelingCode1
Exploiting Context for Robustness to Label Noise in Active Learning—0
DEAL: Difficulty-aware Active Learning for Semantic SegmentationCode1
ReGAL: Rule-Generative Active Learning for Model-in-the-Loop Weak Supervision—0
On the Utility of Active Instance Selection for Few-Shot Learning—0
Active Domain Adaptation via Clustering Uncertainty-weighted EmbeddingsCode1
ALdataset: a benchmark for pool-based active learning—0
Robust Active Learning Strategies for Model Variability—0
Uncertainty Based Active Learning Strategy for Interactive Weakly Supervised Learning through Data Programming—0
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks—0
Identifying Wrongly Predicted Samples: A Method for Active Learning—0
Active learning with RESSPECT: Resource allocation for extragalactic astronomical transientsCode0
Meta-Active Learning for Node Response Prediction in Graphs—0
Pre-trained Language Model Based Active Learning for Sentence Matching—0
Zero-shot Active Learning with Topological Clustering for Multiclass Classification—0
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise TasksCode0
Deep Active Learning for Joint Classification & Segmentation with Weak AnnotatorCode1
Model Exploration with Cost-Aware Learning—0
DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool—0
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective—0
SeqMix: Augmenting Active Sequence Labeling via Sequence MixupCode1
OLALA: Object-Level Active Learning for Efficient Document Layout AnnotationCode1
MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps—0
Show:102550
← PrevPage 79 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