mlsanityData to 14 Oct 2026

A Survey on Active Deep Learning: From Model-driven to Data-driven

arXiv 2101.09933 ↗First posted 25 Jan 2021cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Which samples should be labelled in a large data set is one of the most important problems for trainingof deep learning. So far, a variety of active sample selection strategies related to deep learning havebeen proposed in many literatures. We defined them as Active Deep Learning (ADL) only if theirpredictor is deep model, where the basic learner is called as predictor and the labeling schemes iscalled selector. In this survey, three fundamental factors in selector designation were summarized. Wecategory ADL into model-driven ADL and data-driven ADL, by whether its selector is model-drivenor data-driven. The different characteristics of the two major type of ADL were addressed in indetail respectively. Furthermore, different sub-classes of data-driven and model-driven ADL are alsosummarized and discussed emphatically. The advantages and disadvantages between data-driven ADLand model-driven ADL are thoroughly analyzed. We pointed out that, with the development of deeplearning, the selector in ADL also is experiencing the stage from model-driven to data-driven. Finally,we make discussion on ADL about its uncertainty, explanatory, foundations of cognitive science etc.and survey on the trend of ADL from model-driven to data-driven.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 58 of its 122 references that are in the map. First posted on arXiv 25 Jan 2021.

Builds on

58 of 122 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  9. 2017Deep Bayesian Active Learning with Image Datacited by 819
  10. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  11. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
38 more
  1. 2015Weight Uncertainty in Neural Networkscited by 554
  2. 2020A Survey of Deep Active Learningcited by 554
  3. 2019Learning Loss for Active Learningcited by 336
  4. 2019Variational Adversarial Active Learningcited by 284
  5. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 254
  6. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 219
  7. 2018Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansioncited by 168
  8. 2017On the Sample Complexity of the Linear Quadratic Regulatorcited by 159
  9. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  10. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 157
  11. 2018Model-Based Value Estimation for Efficient Model-Free Reinforcement Learningcited by 156
  12. 2019A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysiscited by 151
  13. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
  14. 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 140
  15. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  16. 2015Learning to Compare Image Patches via Convolutional Neural Networkscited by 109
  17. 2017Learning Active Learning from Datacited by 101
  18. 2019Discriminative Active Learningcited by 98
  19. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 93
  20. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  21. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  22. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  23. 2019Bayesian Generative Active Deep Learningcited by 57
  24. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 54
  25. 2018Adversarial Sampling for Active Learningcited by 51
  26. 2020A Survey of Active Learning for Text Classification using Deep Neural Networkscited by 50
  27. 2019Rethinking deep active learning: Using unlabeled data at model trainingcited by 39
  28. 2016A Benchmark and Comparison of Active Learning for Logistic Regressioncited by 36
  29. 2017Active Learning for Convolutional Neural Networks: A Core-Set Approachcited by 36
  30. 2017Learning Algorithms for Active Learningcited by 30
  31. 2018Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learningcited by 26
  32. 2015Convergence Rates of Active Learning for Maximum Likelihood Estimationcited by 25
  33. 2017Active One-shot Learningcited by 21
  34. 2019Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classificationcited by 15
  35. 2016Asymptotic Analysis of Objectives based on Fisher Information in Active Learningcited by 14
  36. 2016Diet Networks: Thin Parameters for Fat Genomicscited by 12
  37. 2019Active Learning for Segmentation Based on Bayesian Sample Queriescited by 12
  38. 2019An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysiscited by 11

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2023A comprehensive survey on deep active learning in medical image analysiscited by 35
  2. 2023Hybrid Representation-Enhanced Sampling for Bayesian Active Learning in Musculoskeletal Segmentation of Lower Extremitiescited by 4
  3. 2025Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encodercited by 2
  4. 2024ActiveDP: Bridging Active Learning and Data Programmingcited by 1