mlsanityData to 14 Oct 2026

Adversarial Sampling for Active Learning

arXiv 1808.06671 ↗First posted 20 Aug 2018cs.LG cs.CV stat.MLcited by 51

Not on the map. Why?

Abstract (arXiv)

This paper proposes asal, a new GAN based active learning method that generates high entropy samples. Instead of directly annotating the synthetic samples, ASAL searches similar samples from the pool and includes them for training. Hence, the quality of new samples is high and annotations are reliable. To the best of our knowledge, ASAL is the first GAN based AL method applicable to multi-class problems that outperforms random sample selection. Another benefit of ASAL is its small run-time complexity (sub-linear) compared to traditional uncertainty sampling (linear). We present a comprehensive set of experiments on multiple traditional data sets and show that ASAL outperforms similar methods and clearly exceeds the established baseline (random sampling). In the discussion section we analyze in which situations ASAL performs best and why it is sometimes hard to outperform random sample selection.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 15; 2023: 9; 2024: 2; 2025: 6; 2026: 1.

51 papers.

Sort:

By area:

  1. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  2. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  3. 2021Consistency-based Active Learning for Object Detectioncited by 32
  4. 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
  5. 2021Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentationcited by 22
  6. 2023Data-centric Graph Learning: A Surveycited by 22
  7. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  8. 2021Boosting Active Learning via Improving Test Performancecited by 19
  9. 2021MCDAL: Maximum Classifier Discrepancy for Active Learningcited by 18
  10. 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
  11. 2022Deep Active Learning with Noise Stabilitycited by 14
  12. 2021Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learningcited by 11
38 more
  1. 2022Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applicationscited by 11
  2. 2023Accelerating Batch Active Learning Using Continual Learning Techniquescited by 8
  3. 2021When Deep Learners Change Their Mind: Learning Dynamics for Active Learningcited by 6
  4. 2021CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentationcited by 6
  5. 2021Towards General and Efficient Active Learningcited by 6
  6. 2022An Empirical Study on the Efficacy of Deep Active Learning for Image Classificationcited by 6
  7. 2024AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasetscited by 5
  8. 2025Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approachcited by 5
  9. 2021A Survey on Active Deep Learning: From Model-driven to Data-drivencited by 4
  10. 2021Active Learning Under Malicious Mislabeling and Poisoning Attackscited by 3
  11. 2021A Mathematical Analysis of Learning Loss for Active Learning in Regressioncited by 3
  12. 2021Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?cited by 3
  13. 2022Margin-based sampling in high dimensions: When being active is less efficient than staying passivecited by 3
  14. 2022MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detectioncited by 3
  15. 2021Robust Active Learning: Sample-Efficient Training of Robust Deep Learning Modelscited by 2
  16. 2022Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learningcited by 2
  17. 2022Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion Recognitioncited by 2
  18. 2022Temporal Output Discrepancy for Loss Estimation-based Active Learningcited by 2
  19. 2023Active Learning for Video Classification with Frame Level Queriescited by 2
  20. 2025STT-GS: Sample-Then-Transmit Edge Gaussian Splatting with Joint Client Selection and Power Controlcited by 2
  21. 2021Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidancecited by 1
  22. 2023Learning Objective-Specific Active Learning Strategies with Attentive Neural Processescited by 1
  23. 2023Reinforcement-based Display-size Selection for Frugal Satellite Image Change Detectioncited by 1
  24. 2025OFAL: An Oracle-Free Active Learning Frameworkcited by 1
  25. 2021Knowledge Modelling and Active Learning in Manufacturingcited by 0
  26. 2021OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysiscited by 0
  27. 2021Utilizing Active Machine Learning for Quality Assurance: A Case Study of Virtual Car Renderings in the Automotive Industrycited by 0
  28. 2022Towards Robust Deep Active Learning for Scientific Computingcited by 0
  29. 2022Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentationcited by 0
  30. 2022Frugal Reinforcement-based Active Learningcited by 0
  31. 2022Adversarial Virtual Exemplar Learning for Label-Frugal Satellite Image Change Detectioncited by 0
  32. 2023Active Vision Reinforcement Learning under Limited Visual Observabilitycited by 0
  33. 2023Frugal Satellite Image Change Detection with Deep-Net Inversioncited by 0
  34. 2023Towards Comparable Active Learningcited by 0
  35. 2024Active Generation Network of Human Skeleton for Action Recognitioncited by 0
  36. 2025Boosting Active Learning with Knowledge Transfercited by 0
  37. 2025Label-frugal satellite image change detection with generative virtual exemplar learningcited by 0
  38. 2025Image augmentation with invertible networks in interactive satellite image change detectioncited by 0

50 most cited of 51 All 51 (JSON)