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 1251–1300 of 3073 papers

TitleStatusHype
ICS: Total Freedom in Manual Text Classification Supported by Unobtrusive Machine LearningCode1
Active Learning with Safety Constraints—0
Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion RecognitionCode0
DECAL: DEployable Clinical Active Learning—0
covEcho Resource constrained lung ultrasound image analysis tool for faster triaging and active learningCode0
Deep reinforced active learning for multi-class image classification—0
Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning—0
Actively learning to learn causal relationships—0
Towards Efficient Active Learning of PDFACode0
Active Data Discovery: Mining Unknown Data using Submodular Information Measures—0
Federated Learning with Uncertainty via Distilled Predictive Distributions—0
Efficient Human-in-the-loop System for Guiding DNNs AttentionCode0
Physics-informed EDFA Gain Model Based on Active Learning—0
On the reusability of samples in active learningCode5
Weighted Ensembles for Active Learning with Adaptivity—0
In Defense of Core-set: A Density-aware Core-set Selection for Active Learning—0
ScatterSample: Diversified Label Sampling for Data Efficient Graph Neural Network Learning—0
Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning—0
Active Bayesian Causal InferenceCode1
Indirect Active Learning—0
BayesFormer: Transformer with Uncertainty Estimation—0
Midas Loop: A Prioritized Human-in-the-Loop Annotation for Large Scale Multilayer Data—0
Investigating Active Learning Sampling Strategies for Extreme Multi Label Text Classification—0
Support Vector Machines under Adversarial Label Contamination—0
An optimal transport approach for selecting a representative subsample with application in efficient kernel density estimation—0
Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning—0
Characterizing the robustness of Bayesian adaptive experimental designs to active learning biasCode0
Opinion Spam Detection: A New Approach Using Machine Learning and Network-Based Algorithms—0
Deep Active Learning with Noise Stability—0
Active Labeling: Streaming Stochastic GradientsCode0
SALAD: Source-free Active Label-Agnostic Domain Adaptation for Classification, Segmentation and DetectionCode0
Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation—0
Active Learning Through a Covering LensCode1
Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction—0
PyRelationAL: a python library for active learning research and developmentCode1
CELEST: Federated Learning for Globally Coordinated Threat Detection—0
Tackling Provably Hard Representative Selection via Graph Neural Networks—0
Bayesian Active Learning with Fully Bayesian Gaussian ProcessesCode1
Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning—0
A Simple yet Effective Framework for Active Learning to Rank—0
Probability trees and the value of a single intervention—0
Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling—0
Active learning of causal probability trees—0
Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous DrivingCode0
SCAF: Skip-Connections in Auto-encoder for Face alignment with few annotated data—0
Self-supervised Assisted Active Learning for Skin Lesion SegmentationCode1
ALLSH: Active Learning Guided by Local Sensitivity and Hardness—0
Towards Computationally Feasible Deep Active LearningCode1
The Right Tool for the Job: Matching Active Learning Techniques to Learning ObjectivesCode0
One Size Does Not Fit All: The Case for Personalised Word Complexity Models—0
Show:102550
← PrevPage 26 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