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 1326–1350 of 3073 papers

TitleStatusHype
Confidence Calibration for Convolutional Neural Networks Using Structured Dropout—0
Confidence-based Active Learning Methods for Machine Translation—0
Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge—0
Detecting Repeating Objects using Patch Correlation Analysis—0
ALPINE: Active Link Prediction using Network Embedding—0
Deterministic Langevin Unconstrained Optimization with Normalizing Flows—0
ActiveLab: Active Learning with Re-Labeling by Multiple Annotators—0
Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study—0
DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures—0
Cell Library Characterization for Composite Current Source Models Based on Gaussian Process Regression and Active Learning—0
Dialog Policy Learning for Joint Clarification and Active Learning Queries—0
Diameter-Based Active Learning—0
Diameter-based Interactive Structure Discovery—0
Differentiable Submodular Maximization—0
ALVIN: Active Learning Via INterpolation—0
Difficult Cases: From Data to Learning, and Back—0
Active Learning Guided Fine-Tuning for enhancing Self-Supervised Based Multi-Label Classification of Remote Sensing Images—0
Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography—0
Diffusion-based Deep Active Learning—0
Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation—0
DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning—0
Distribution-Dependent Sample Complexity of Large Margin Learning—0
DIRECT: Deep Active Learning under Imbalance and Label Noise—0
Confidence Adjusted Surprise Measure for Active Resourceful Trials (CA-SMART): A Data-driven Active Learning Framework for Accelerating Material Discovery under Resource Constraints—0
AdaptiFont: Increasing Individuals' Reading Speed with a Generative Font Model and Bayesian Optimization—0
Show:102550
← PrevPage 54 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