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 2951–2975 of 3073 papers

TitleStatusHype
Reducing Aleatoric and Epistemic Uncertainty through Multi-modal Data AcquisitionCode0
Finding the Homology of Decision Boundaries with Active LearningCode0
Find Rhinos without Finding Rhinos: Active Learning with Multimodal Imagery of South African Rhino HabitatsCode0
Learning to Caption Images through a Lifetime by Asking QuestionsCode0
Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-OrganizationCode0
Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument SegmentationCode0
Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain ShiftCode0
A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT ImagesCode0
A Variance Maximization Criterion for Active LearningCode0
Active Learning for Argument Strength EstimationCode0
FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher InformationCode0
OpenAL: An Efficient Deep Active Learning Framework for Open-Set Pathology Image ClassificationCode0
OpenAL: Evaluation and Interpretation of Active Learning StrategiesCode0
To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer ModelsCode0
Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version)Code0
FOCAL: A Cost-Aware Video Dataset for Active LearningCode0
SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac SignalsCode0
Active Learning for Graph EmbeddingCode0
Automatic Segmentation of the Spinal Cord Nerve RootletsCode0
FOIT: Fast Online Instance Transfer for Improved EEG Emotion RecognitionCode0
LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource LanguagesCode0
OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]Code0
Reducing the Long Tail Losses in Scientific Emulations with Active LearningCode0
TAAL: Test-time Augmentation for Active Learning in Medical Image SegmentationCode0
Active Learning for Abstractive Text SummarizationCode0
Show:102550
← PrevPage 119 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