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 51–100 of 3073 papers

TitleStatusHype
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image ClassificationCode1
AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced DatasetsCode1
Active Test-Time Adaptation: Theoretical Analyses and An AlgorithmCode1
Active Statistical InferenceCode1
Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann EstimatorsCode1
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow ParadigmCode1
SelectLLM: Can LLMs Select Important Instructions to Annotate?Code1
Revisiting Active Learning in the Era of Vision Foundation ModelsCode1
Querying Easily Flip-flopped Samples for Deep Active LearningCode1
ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic SegmentationCode1
Inconsistency-Based Data-Centric Active Open-Set AnnotationCode1
Weakly Supervised Point Cloud Semantic Segmentation via Artificial OracleCode1
Entropic Open-set Active LearningCode1
Generalized Category Discovery with Large Language Models in the LoopCode1
Semi-Supervised Active Learning for Semantic Segmentation in Unknown Environments Using Informative Path PlanningCode1
Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain ShiftsCode1
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentialsCode1
Data-Driven Autoencoder Numerical Solver with Uncertainty Quantification for Fast Physical SimulationsCode1
FreeAL: Towards Human-Free Active Learning in the Era of Large Language ModelsCode1
Evidential Uncertainty Quantification: A Variance-Based PerspectiveCode1
Active Prompt Learning in Vision Language ModelsCode1
Active Transfer Learning for Efficient Video-Specific Human Pose EstimationCode1
Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient SelectionCode1
LLMaAA: Making Large Language Models as Active AnnotatorsCode1
A comprehensive survey on deep active learning in medical image analysisCode1
Open-CRB: Towards Open World Active Learning for 3D Object DetectionCode1
TacoGFN: Target-conditioned GFlowNet for Structure-based Drug DesignCode1
Towards Free Data Selection with General-Purpose ModelsCode1
Explaining Predictive Uncertainty with Information Theoretic Shapley ValuesCode1
ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular GenerationCode1
Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic SegmentationCode1
COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image SegmentationCode1
Divide and Adapt: Active Domain Adaptation via Customized LearningCode1
ProbVLM: Probabilistic Adapter for Frozen Vision-Language ModelsCode1
M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis TasksCode1
LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient LearningCode1
ActiveGLAE: A Benchmark for Deep Active Learning with TransformersCode1
Towards Balanced Active Learning for Multimodal ClassificationCode1
Memory-Based Dual Gaussian Processes for Sequential LearningCode1
infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-informationCode1
Parallelized Acquisition for Active Learning using Monte Carlo SamplingCode1
Label-Efficient Learning in Agriculture: A Comprehensive ReviewCode1
Machine-learning-accelerated simulations to enable automatic surface reconstructionCode1
Disentangled Multi-Fidelity Deep Bayesian Active LearningCode1
You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic SegmentationCode1
Prediction-Oriented Bayesian Active LearningCode1
A dynamic Bayesian optimized active recommender system for curiosity-driven Human-in-the-loop automated experimentsCode1
Creating Custom Event Data Without Dictionaries: A Bag-of-TricksCode1
AISecKG: Knowledge Graph Dataset for Cybersecurity EducationCode1
Adaptive Superpixel for Active Learning in Semantic SegmentationCode1
Show:102550
← PrevPage 2 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