Uncertainty Sampling

Uncertainty sampling is an active learning technique that strategically selects data points for labeling, prioritizing those where a model's prediction is most uncertain. Current research focuses on improving uncertainty estimation methods, particularly for complex data structures like graphs and time series, and integrating uncertainty sampling with other active learning strategies like diversity sampling to enhance efficiency. This approach is crucial for optimizing data annotation in resource-constrained scenarios, such as federated learning and medical image analysis, leading to more efficient and effective machine learning model training. The development of robust uncertainty estimators and their application across diverse domains are key areas of ongoing investigation.

Papers

August 30, 2024

Sparse Uncertainty-Informed Sampling from Federated Streaming Data
Manuel Röder, Frank-Michael Schleif
Many Sparse Data Stream Local Adaptivity Federated Data Uncertainty Sampling Label Extraction Front Diverse Batch

June 6, 2024

Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
Abdullah Akgül, Manuel Haußmann, Melih Kandemir
Large Relevance Improvement Model Based Offline Reinforcement Learning Uncertainty Propagation Reliable Uncertainty Uncertainty Sampling Reward Ambiguity Model Based Policy

May 2, 2024

Uncertainty for Active Learning on Graphs
Dominik Fuchsgruber, Tom Wollschläger, Bertrand Charpentier, Antonio Oroz, Stephan Günnemann
Graph Drawing Active Learning Ground Truth High Uncertainty Anticipation Uncertainty Estimation Predictive Uncertainty Uncertainty Modeling Uncertainty Sampling

March 6, 2024

Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Training
Paul Doucet, Benjamin Estermann, Till Aczel, Roger Wattenhofer
Active Learning High Uncertainty Anticipation Self Supervised Pre Training Diverse Datasets Diversity Enhancement Self Supervised Pre Trained Model Uncertainty Sampling Sample Diversity

March 3, 2024

Improving Uncertainty Sampling with Bell Curve Weight Function
Zan-Kai Chong, Hiroyuki Ohsaki, Bok-Min Goi
Uncertainty Sampling Passive Learning Unbiased Sampling Weighting Function

January 9, 2024

Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning
Kuo Yang, Duo Li, Menghan Hu, Guangtao Zhai, Xiaokang Yang, Xiao-Ping Zhang
Semi Supervised Learning Pseudo Label Uncertainty Sampling Label Ambiguity Long Tailed Semi Supervised Learning Pseudo Label Sampling

September 21, 2023

Evidential uncertainty sampling for active learning
Arthur Hoarau, Vincent Lemaire, Arnaud Martin, Jean-Christophe Dubois, Yolande Le Gall
Active Learning Belief Function Uncertainty Sampling Evidential Uncertainty

May 24, 2023

Sampling-based Uncertainty Estimation for an Instance Segmentation Network
Florian Heidecker, Ahmad El-Khateeb, Bernhard Sick
Machine Learning Mixture Model Focal Loss Mask RCNN Uncertainty Sampling Instance Segmentation Network Uncertainty Approximation

March 30, 2023

OpenMix: Exploring Outlier Samples for Misclassification Detection
Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu
Confidence Estimation Outlier Exposure Uncertainty Sampling Outlier Sample Misclassification Detection

February 5, 2023

Active Learning in Brain Tumor Segmentation with Uncertainty Sampling, Annotation Redundancy Restriction, and Data Initialization
Daniel D Kim, Rajat S Chandra, Jian Peng, Jing Wu, Xue Feng, Michael Atalay, Chetan Bettegowda, Craig Jones, Haris Sair, Wei-hua Liao, Chengzhang Zhu, Beiji Zou, Li Yang, Anahita Fathi Kazerooni, Ali Nabavizadeh, Harrison X Bai, Zhicheng Jiao
Active Learning Pre Trained Brain Tumor Segmentation 3D U Net Uncertainty Sampling 3D Medical Imaging

January 18, 2023

Active learning for medical image segmentation with stochastic batches
Mélanie Gaillochet, Christian Desrosiers, Hervé Lombaert
Active Learning Medical Image Segmentation Medical Image Segmentation Datasets Uncertainty Sampling Mi Segmentation

December 6, 2022

MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection
Dong Liang, Jing-Wei Zhang, Ying-Peng Tang, Sheng-Jun Huang
Active Learning Aerial Object Detection Uncertainty Sampling Novel Active Learning Class Balancing Technique

October 27, 2022

Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learning
Kevin Miller, Jeff Calder
Active Learning Uncertainty Sampling Graph Based Active Learning

October 26, 2022

Uncertainty Sentence Sampling by Virtual Adversarial Perturbation
Hanshan Zhang, Zhen Zhang, Hongfei Jiang, Yang Song
Active Learning Adversarial Perturbation Uncertainty Sampling

September 17, 2022

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network
Takuya Kanazawa, Chetan Gupta
Uncertainty Quantification Single Neural Network Predictive Distribution Deterministic Neural Network Uncertainty Sampling Uncertainty Quantification Method Point Forecasting

May 5, 2022

Uncertainty-Based Non-Parametric Active Peak Detection
Praneeth Narayanamurthy, Urbashi Mitra
Uncertainty Sampling Peak Detection Passive Localization