mlsanityData to 14 Oct 2026

A Survey on Deep Active Learning: Recent Advances and New Frontiers

arXiv 2405.00334 ↗First posted 1 May 2024cs.LGcited by 54

Not on the map. Why?

Abstract (arXiv)

Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label new selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due to its broad applicability, yet its survey papers, especially for deep learning-based active learning (DAL), remain scarce. Therefore, we conduct an advanced and comprehensive survey on DAL. We first introduce reviewed paper collection and filtering. Second, we formally define the DAL task and summarize the most influential baselines and widely used datasets. Third, we systematically provide a taxonomy of DAL methods from five perspectives, including annotation types, query strategies, deep model architectures, learning paradigms, and training processes, and objectively analyze their strengths and weaknesses. Then, we comprehensively summarize main applications of DAL in Natural Language Processing (NLP), Computer Vision (CV), and Data Mining (DM), etc. Finally, we discuss challenges and perspectives after a detailed analysis of current studies. This work aims to serve as a useful and quick guide for researchers in overcoming difficulties in DAL. We hope that this survey will spur further progress in this burgeoning field.

Key facts. Cited by 54 papers in the map (data through 14 Oct 2026). Builds on 126 of its 213 references that are in the map. First posted on arXiv 1 May 2024.

Builds on

126 of 213 references.

References · 126

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  9. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  10. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  11. 2017Deep Bayesian Active Learning with Image Datacited by 819
  12. 2020A Survey of Deep Active Learningcited by 554
38 more
  1. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  2. 2019Learning Loss for Active Learningcited by 336
  3. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  4. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
  5. 2019Variational Adversarial Active Learningcited by 284
  6. 2020On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselinescited by 255
  7. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  8. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  9. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  10. 2019A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysiscited by 151
  11. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  12. 2022Dataset Pruning: Reducing Training Data by Examining Generalization Influencecited by 133
  13. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  14. 2021Batch Active Learning at Scalecited by 127
  15. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  16. 2017Learning Active Learning from Datacited by 101
  17. 2020Fast active learning for pure exploration in reinforcement learningcited by 92
  18. 2022A Comparative Survey of Deep Active Learningcited by 89
  19. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 87
  20. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  21. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 84
  22. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  23. 2021Multiple instance active learning for object detectioncited by 77
  24. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 75
  25. 2019Active Adversarial Domain Adaptationcited by 73
  26. 2017Generative Adversarial Active Learningcited by 70
  27. 2022Active Learning Through a Covering Lenscited by 66
  28. 2022Active Learning by Feature Mixingcited by 63
  29. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  30. 2020State-Relabeling Adversarial Active Learningcited by 60
  31. 2021Revisiting Uncertainty-based Query Strategies for Active Learning with Transformerscited by 60
  32. 2019Bayesian Generative Active Deep Learningcited by 57
  33. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 57
  34. 2017Active Learning for Graph Embeddingcited by 54
  35. 2023Active Learning Principles for In-Context Learning with Large Language Modelscited by 54
  36. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  37. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  38. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52

50 most cited of 126 All 126 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 23; 2026: 25.

54 papers.

Sort:

By area:

  1. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  2. 2025Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuningcited by 12
  3. 2025Consensus-Driven Active Model Selectioncited by 8
  4. 2026MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safetycited by 8
  5. 2025Active Test-time Vision-Language Navigationcited by 7
  6. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  7. 2025Cohort-Based Active Modality Acquisitioncited by 5
  8. 2025Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimizationcited by 5
  9. 2026DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderationcited by 4
  10. 2024VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedbackcited by 2
  11. 2024LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Trainingcited by 2
  12. 2025Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capablescited by 2
38 more
  1. 2025PICore: Physics-Informed Unsupervised Coreset Selection for Data Efficient Neural Operator Trainingcited by 2
  2. 2025Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemblecited by 2
  3. 2025IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detectioncited by 2
  4. 2026Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categoriescited by 2
  5. 2026Loss-Driven Bayesian Active Learningcited by 2
  6. 2026Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Imagescited by 2
  7. 2025A model-agnostic active learning approach for animal detection from camera trapscited by 1
  8. 2025SoK: Data Minimization in Machine Learningcited by 1
  9. 2025SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentationcited by 1
  10. 2026Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RLcited by 1
  11. 2026UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shiftscited by 1
  12. 2026AvAtar: Learning to Align via Active Optimal Transportcited by 1
  13. 2024Sparse Linear Bandits with Blocking Constraintscited by 0
  14. 2024Federated Learning with Workload Reduction through Partial Training of Client Models and Entropy-Based Data Selectioncited by 0
  15. 2025ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languagescited by 0
  16. 2025Hierarchical graph sampling based minibatch learning with chain preservation and variance reductioncited by 0
  17. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0
  18. 2025PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Modelscited by 0
  19. 2025Lifelong Evolution: Collaborative Learning between Large and Small Language Models for Continuous Emergent Fake News Detectioncited by 0
  20. 2025Metric Matters: A Formal Evaluation of Similarity Measures in Active Learning for Cyber Threat Intelligencecited by 0
  21. 2025Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classificationcited by 0
  22. 2025Unsupervised Active Learning via Natural Feature Progressive Frameworkcited by 0
  23. 2025Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networkscited by 0
  24. 2025Neural surrogates for designing gravitational wave detectorscited by 0
  25. 2025Active Learning for GCN-based Action Recognitioncited by 0
  26. 2026Lightweight Edge Learning via Dataset Pruningcited by 0
  27. 2026Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimatorscited by 0
  28. 2026Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AIcited by 0
  29. 2026Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimizationcited by 0
  30. 2026Informed Machine Learning with Knowledge Landmarkscited by 0
  31. 2026Feature Weighting Improves Pool-Based Sequential Active Learning for Regressioncited by 0
  32. 2026RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagerycited by 0
  33. 2026Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensingcited by 0
  34. 2026M3: Reframing Training Measures for Discretized Physical Simulationscited by 0
  35. 2026Data-Efficient Neural Operator Training via Physics-Based Active Learningcited by 0
  36. 2026QueryMarket: Cost-Aware Online Active Learning in Data Marketscited by 0
  37. 2026Group-invariant Coresets for Data-efficient Active Learningcited by 0
  38. 2026Active few-shot segmentation by reinforcing data selectioncited by 0

50 most cited of 54 All 54 (JSON)