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 1601–1650 of 3073 papers

TitleStatusHype
THMA: Tencent HD Map AI System for Creating HD Map Annotations—0
Thompson Sampling for Dynamic Pricing—0
Thompson sampling for improved exploration in GFlowNets—0
Ticket-BERT: Labeling Incident Management Tickets with Language Models—0
t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning—0
TOCO: A Framework for Compressing Neural Network Models Based on Tolerance Analysis—0
To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation—0
Toward Machine-Guided, Human-Initiated Explanatory Interactive Learning—0
Towards Active Learning Based Smart Assistant for Manufacturing—0
Towards Active Learning for Action Spotting in Association Football Videos—0
Towards a Foundation Model for Physics-Informed Neural Networks: Multi-PDE Learning with Active Sampling—0
Towards Algorithmic Fairness in Space-Time: Filling in Black Holes—0
Towards an active-learning approach to resource allocation for population-based damage prognosis—0
Towards a Tool for Interactive Concept Building for Large Scale Analysis in the Humanities—0
Towards Better Response Times and Higher-Quality Queries in Interactive Knowledge Base Debugging—0
Towards Comparable Active Learning—0
Towards Computationally Feasible Deep Active Learning—0
Towards Cost-Effective Learning: A Synergy of Semi-Supervised and Active Learning—0
Towards countering hate speech against journalists on social media—0
Towards Deep Active Learning in Avian Bioacoustics—0
Towards Efficient Active Learning in NLP via Pretrained Representations—0
Towards Efficient Disaster Response via Cost-effective Unbiased Class Rate Estimation through Neyman Allocation Stratified Sampling Active Learning—0
Towards Explainable, Safe Autonomous Driving with Language Embeddings for Novelty Identification and Active Learning: Framework and Experimental Analysis with Real-World Data Sets—0
Towards Fewer Labels: Support Pair Active Learning for Person Re-identification—0
Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder—0
Towards Global-Scale Crowd+AI Techniques to Map and Assess Sidewalks for People with Disabilities—0
Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection—0
Towards more Reliable Transfer Learning—0
Towards ontology driven learning of visual concept detectors—0
Towards Overcoming Practical Obstacles to Deploying Deep Active Learning—0
Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection—0
Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection—0
Representative Subset Selection for Efficient Fine-Tuning in Self-Supervised Speech Recognition—0
Towards Unconstrained 2D Pose Estimation of the Human Spine—0
Toward Supervised Anomaly Detection—0
Towards Visual Explainable Active Learning for Zero-Shot Classification—0
Training Data Distribution Search with Ensemble Active Learning—0
Transferable Query Selection for Active Domain Adaptation—0
Transfer Active Learning For Graph Neural Networks—0
TrustAL: Trustworthy Active Learning using Knowledge Distillation—0
Trust and Believe -- Should We? Evaluating the Trustworthiness of Twitter Users—0
Tuning Deep Active Learning for Semantic Role Labeling—0
Turning silver into gold: error-focused corpus reannotation with active learning—0
Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling—0
Two Stream Active Query Suggestion for Active Learning in Connectomics—0
Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction—0
U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario—0
Ulcerative Colitis Mayo Endoscopic Scoring Classification with Active Learning and Generative Data Augmentation—0
Ultra-Reliable and Low-Latency Vehicular Communication: An Active Learning Approach—0
UMat: Uncertainty-Aware Single Image High Resolution Material Capture—0
Show:102550
← PrevPage 33 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