Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement
Not on the map. Why?
Abstract (arXiv)
In the era of data-driven intelligence, the paradox of data abundance and annotation scarcity has emerged as a critical bottleneck in the advancement of machine learning. This paper gives a detailed overview of Active Learning (AL), which is a strategy in machine learning that helps models achieve better performance using fewer labeled examples. It introduces the basic concepts of AL and discusses how it is used in various fields such as computer vision, natural language processing, transfer learning, and real-world applications. The paper focuses on important research topics such as uncertainty estimation, handling of class imbalance, domain adaptation, fairness, and the creation of strong evaluation metrics and benchmarks. It also shows that learning methods inspired by humans and guided by questions can improve data efficiency and help models learn more effectively. In addition, this paper talks about current challenges in the field, including the need to rebuild trust, ensure reproducibility, and deal with inconsistent methodologies. It points out that AL often gives better results than passive learning, especially when good evaluation measures are used. This work aims to be useful for both researchers and practitioners by providing key insights and proposing directions for future progress in active learning.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 93 of its 117 references that are in the map. First posted on arXiv 21 Apr 2025.
Builds on
93 of 117 references.
References · 93
- 2018A Survey on Deep Transfer Learningcited by 417
- 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
- 2019REPAIR: Removing Representation Bias by Dataset Resamplingcited by 157
- 2017Domain Adaptation for Visual Applications: A Comprehensive Surveycited by 127
- 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
- 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
- 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 72
- 2022Active Learning by Feature Mixingcited by 63
- 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
- 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
- 2016The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narrativescited by 41
- 2016Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemescited by 40
38 more
- 2022A Survey of Active Learning for Natural Language Processingcited by 40
- 2019Parting with Illusions about Deep Active Learningcited by 38
- 2020DEAL: Difficulty-aware Active Learning for Semantic Segmentationcited by 32
- 2021On the Importance of Effectively Adapting Pretrained Language Models for Active Learningcited by 31
- 2022GALAXY: Graph-based Active Learning at the Extremecited by 29
- 2017Learning by Asking Questionscited by 25
- 2020VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learningcited by 25
- 2023Active Prompt Learning in Vision Language Modelscited by 25
- 2017Active Convolution: Learning the Shape of Convolution for Image Classificationcited by 24
- 2019Epistemic Uncertainty Samplingcited by 24
- 2020Active Learning under Label Shiftcited by 23
- 2020Active Learning: Problem Settings and Recent Developmentscited by 23
- 2019An Adaptive Supervision Framework for Active Learning in Object Detectioncited by 20
- 2020Stopping criterion for active learning based on deterministic generalization boundscited by 20
- 2022A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processingcited by 20
- 2021Convergence of Uncertainty Sampling for Active Learningcited by 19
- 2024Deep Bayesian Active Learning for Preference Modeling in Large Language Modelscited by 19
- 2019Domain Adversarial Reinforcement Learning for Partial Domain Adaptationcited by 16
- 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
- 2021Can Active Learning Preemptively Mitigate Fairness Issues?cited by 15
- 2021Class-Balanced Active Learning for Image Classificationcited by 15
- 2024FairAIED: Navigating Fairness, Bias, and Ethics in Educational AI Applicationscited by 15
- 2023Divide and Adapt: Active Domain Adaptation via Customized Learningcited by 13
- 2018On the Relationship between Data Efficiency and Error for Uncertainty Samplingcited by 12
- 2017Active Learning for Visual Question Answering: An Empirical Studycited by 11
- 2022Active Learning Over Multiple Domains in Natural Language Taskscited by 11
- 2022TiDAL: Learning Training Dynamics for Active Learningcited by 11
- 2023Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLPcited by 11
- 2024A Cross-Domain Benchmark for Active Learningcited by 11
- 2020Empowering Active Learning to Jointly Optimize System and User Demandscited by 10
- 2023Best Practices in Active Learning for Semantic Segmentationcited by 10
- 2022Characterizing the robustness of Bayesian adaptive experimental designs to active learning biascited by 8
- 2023AmbieGen: A Search-based Framework for Autonomous Systems Testingcited by 8
- 2023ALWOD: Active Learning for Weakly-Supervised Object Detectioncited by 8
- 2024Generative AI for Enhancing Active Learning in Education: A Comparative Study of GPT-3.5 and GPT-4 in Crafting Customized Test Questionscited by 8
- 2020Discriminative Active Learning for Domain Adaptationcited by 7
- 2021Visual Transformer for Task-aware Active Learningcited by 7
- 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
50 most cited of 93 All 93 (JSON)
Built on by
Not cited yet.