Active Learning

Active learning is a machine learning paradigm focused on optimizing data labeling efficiency by strategically selecting the most informative samples for annotation from a larger unlabeled pool. Current research emphasizes developing novel acquisition functions and data pruning strategies to reduce computational costs associated with large datasets, exploring the integration of active learning with various model architectures (including deep neural networks, Gaussian processes, and language models), and addressing challenges like privacy preservation and handling open-set noise. This approach holds significant promise for reducing the substantial cost and effort of data labeling in diverse fields, ranging from image classification and natural language processing to materials science and healthcare.

Papers

March 9, 2022

Onception: Active Learning with Expert Advice for Real World Machine Translation
Vânia Mendonça, Ricardo Rei, Luisa Coheur, Alberto Sardinha
Active Learning Machine Translation Machine Translation Model

March 4, 2022

March 3, 2022

Informative Path Planning for Active Learning in Aerial Semantic Mapping
Julius Rückin, Liren Jin, Federico Magistri, Cyrill Stachniss, Marija Popović
Semantic Segmentation Active Learning Unmanned Aerial Vehicle Model Uncertainty Aerial Imagery Informative Path Planning Terrain Analysis

March 2, 2022

February 28, 2022

Active learning with binary models for real time data labelling
Ankush Deshmukh, Bhargava B C, A V Narasimhadhan
Deep Learning Machine Learning Active Learning Supervised Learning Machine Learning Algorithm Data Labeling Binary Model Label Extraction

February 27, 2022

Bayesian Active Learning for Discrete Latent Variable Models
Aditi Jha, Zoe C. Ashwood, Jonathan W. Pillow
Active Learning Latent Variable Model Latent State Discrete Latent Variable Bayesian Active Learning Discrete Latent

February 25, 2022

Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning
Feifei Shao, Yawei Luo, Ping Liu, Jie Chen, Yi Yang, Yulei Lu, Jun Xiao
Semantic Segmentation Point Cloud Active Learning Point Cloud Semantic Segmentation

February 23, 2022

Modulation and signal class labelling using active learning and classification using machine learning
Bhargava B C, Ankush Deshmukh, A V Narasimhadhan
Machine Learning Classification Code Active Learning Digital Modulation Signal Classification Active Learning Algorithm Class Label Higher Order Modulation

February 21, 2022

February 17, 2022

Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs
Stefano Teso, Antonio Vergari
High Efficiency Active Learning Probabilistic Model Structured Output Probabilistic Circuit Interactive Learning Output Space

February 14, 2022

D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentation
Tsung-Han Wu, Yi-Syuan Liou, Shao-Ji Yuan, Hsin-Ying Lee, Tung-I Chen, Kuan-Chih Huang, Winston H. Hsu
Semantic Segmentation Domain Adaptation Active Learning Active Domain Adaptation

February 11, 2022

Fast Rates in Pool-Based Batch Active Learning
Claudio Gentile, Zhilei Wang, Tong Zhang
Active Learning Greedy Algorithm Test Oracle Fast Rate Pool Based Active Learning Label Complexity

February 10, 2022

Improving performance of aircraft detection in satellite imagery while limiting the labelling effort: Hybrid active learning
Julie Imbert, Gohar Dashyan, Alex Goupilleau, Tugdual Ceillier, Marie-Caroline Corbineau
Active Learning System Performance Satellite Imagery Uncertainty Based Active Learning Labeling Effort Aircraft Detection

February 9, 2022

February 8, 2022

A Lagrangian Duality Approach to Active Learning
Juan Elenter, Navid NaderiAlizadeh, Alejandro Ribeiro
Active Learning Primal Dual Lagrangian System Active Sampling Constrained Learning Pool Based Active Learning

February 6, 2022

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
Guy Hacohen, Avihu Dekel, Daphna Weinshall
Active Learning Semi Supervised Deep Active Learning Local Authority Budget Low Budget

Active Learning

Papers

Onception: Active Learning with Expert Advice for Real World Machine Translation

BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation

Passive and Active Learning of Driver Behavior from Electric Vehicles

Informative Path Planning for Active Learning in Aerial Semantic Mapping

Neural Galerkin Schemes with Active Learning for High-Dimensional Evolution Equations

Information Gain Propagation: a new way to Graph Active Learning with Soft Labels

Active learning with binary models for real time data labelling

Bayesian Active Learning for Discrete Latent Variable Models

Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning

Modulation and signal class labelling using active learning and classification using machine learning

t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning

A new data augmentation method for intent classification enhancement and its application on spoken conversation datasets

Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs

D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentation

Fast Rates in Pool-Based Batch Active Learning

Improving performance of aircraft detection in satellite imagery while limiting the labelling effort: Hybrid active learning

Active Learning Improves Performance on Symbolic RegressionTasks in StackGP

Improving greedy core-set configurations for active learning with uncertainty-scaled distances

A Lagrangian Duality Approach to Active Learning

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets