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 1–50 of 3073 papers

TitleStatusHype
Active Learning for Neural PDE SolversCode5
On the reusability of samples in active learningCode5
ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object DetectionCode4
Let's Verify Step by StepCode4
From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point SupervisionCode3
Sailing AI by the Stars: A Survey of Learning from Rewards in Post-Training and Test-Time Scaling of Large Language ModelsCode2
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMsCode2
DCoM: Active Learning for All LearnersCode2
EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy NetworkCode2
Generative Active Learning for Long-tailed Instance SegmentationCode2
Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary DataCode2
Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theoryCode2
Physics-informed active learning for accelerating quantum chemical simulationsCode2
Active Generalized Category DiscoveryCode2
ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented AgentsCode2
Transductive Active Learning: Theory and ApplicationsCode2
Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learningCode2
Multi-Fidelity Active Learning with GFlowNetsCode2
DeepEdit: Deep Editable Learning for Interactive Segmentation of 3D Medical ImagesCode2
AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three WeeksCode2
Streaming Active Learning with Deep Neural NetworksCode2
Active Prompting with Chain-of-Thought for Large Language ModelsCode2
Trieste: Efficiently Exploring The Depths of Black-box Functions with TensorFlowCode2
POTATO: The Portable Text Annotation ToolCode2
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
Active-Learning-as-a-Service: An Automatic and Efficient MLOps System for Data-Centric AICode2
Human-in-the-Loop Large-Scale Predictive Maintenance of WorkstationsCode2
DeepCore: A Comprehensive Library for Coreset Selection in Deep LearningCode2
MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical ImagesCode2
CriticLean: Critic-Guided Reinforcement Learning for Mathematical FormalizationCode1
InvDesFlow-AL: Active Learning-based Workflow for Inverse Design of Functional MaterialsCode1
Efficient Process Reward Model Training via Active LearningCode1
Generating π-Functional Molecules Using STGG+ with Active LearningCode1
Enhanced Multi-Object Tracking Using Pose-based Virtual Markers in 3x3 BasketballCode1
Post-hoc Probabilistic Vision-Language ModelsCode1
Spectral-Spatial Transformer with Active Transfer Learning for Hyperspectral Image ClassificationCode1
AL-GTD: Deep Active Learning for Gaze Target DetectionCode1
Diversify and Conquer: Diversity-Centric Data Selection with Iterative RefinementCode1
Causal-Guided Active Learning for Debiasing Large Language ModelsCode1
I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement ParadigmCode1
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple HumansCode1
Transductive Active Learning with Application to Safe Bayesian OptimizationCode1
Dataset Quantization with Active Learning based Adaptive SamplingCode1
ALPBench: A Benchmark for Active Learning Pipelines on Tabular DataCode1
Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center DatasetCode1
SS-ADA: A Semi-Supervised Active Domain Adaptation Framework for Semantic SegmentationCode1
Understanding active learning of molecular docking and its applicationsCode1
CloudS2Mask: A novel deep learning approach for improved cloud and cloud shadow masking in Sentinel-2 imageryCode1
Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)Code1
Making Better Use of Unlabelled Data in Bayesian Active LearningCode1
Show:102550
← PrevPage 1 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