mlsanityData to 7 Oct 2026

Learning Loss for Active Learning

arXiv 1905.03677 ↗First posted 9 May 2019cs.CV cs.LGcited by 335

Not on the map. Why?

Abstract (arXiv)

The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as uncertain. A variety of recent methods have been proposed to apply active learning to deep networks but most of them are either designed specific for their target tasks or computationally inefficient for large networks. In this paper, we propose a novel active learning method that is simple but task-agnostic, and works efficiently with the deep networks. We attach a small parametric module, named "loss prediction module," to a target network, and learn it to predict target losses of unlabeled inputs. Then, this module can suggest data that the target model is likely to produce a wrong prediction. This method is task-agnostic as networks are learned from a single loss regardless of target tasks. We rigorously validate our method through image classification, object detection, and human pose estimation, with the recent network architectures. The results demonstrate that our method consistently outperforms the previous methods over the tasks.

Key facts. Cited by 335 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 62; 2022: 68; 2023: 65; 2024: 61; 2025: 41; 2026: 38.

335 papers.

Sort:

By area:

  1. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  2. 2021Batch Active Learning at Scalecited by 127
  3. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  4. 2022A Comparative Survey of Deep Active Learningcited by 88
  5. 2021Influence Selection for Active Learningcited by 82
  6. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  7. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  8. 2021Multiple instance active learning for object detectioncited by 77
  9. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 72
  10. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  11. 2022Active Learning by Feature Mixingcited by 63
  12. 2022Active Learning Through a Covering Lenscited by 62
38 more
  1. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  2. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  3. 2021A Survey on Green Deep Learningcited by 52
  4. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  5. 2021SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistencycited by 47
  6. 2021Reducing Label Effort: Self-Supervised meets Active Learningcited by 42
  7. 2022PseudoClick: Interactive Image Segmentation with Click Imitationcited by 42
  8. 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
  9. 2022A Survey of Active Learning for Natural Language Processingcited by 40
  10. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  11. 2023Continuous Learning for Android Malware Detectioncited by 33
  12. 2024Active Evaluation Acquisition for Efficient LLM Benchmarkingcited by 33
  13. 2021Consistency-based Active Learning for Object Detectioncited by 32
  14. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  15. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  16. 2021All you need are a few pixels: semantic segmentation with PixelPickcited by 30
  17. 2021Improving Contrastive Learning on Imbalanced Seed Data via Open-World Samplingcited by 30
  18. 2022Plug and Play Active Learning for Object Detectioncited by 28
  19. 2021Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detectioncited by 27
  20. 2021Unsupervised Selective Labeling for More Effective Semi-Supervised Learningcited by 27
  21. 2022PT4AL: Using Self-Supervised Pretext Tasks for Active Learningcited by 27
  22. 2022In Defense of Core-set: A Density-aware Core-set Selection for Active Learningcited by 26
  23. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  24. 2023Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shiftscited by 26
  25. 2022Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernelscited by 25
  26. 2023Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessmentcited by 25
  27. 2022A Lagrangian Duality Approach to Active Learningcited by 24
  28. 2022Few-Shot Continual Active Learning by a Robotcited by 24
  29. 2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 24
  30. 2024Adaptive teachers for amortized samplerscited by 23
  31. 2022How Much More Data Do I Need? Estimating Requirements for Downstream Taskscited by 22
  32. 2021Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learningcited by 20
  33. 2023Active learning for medical image segmentation with stochastic batchescited by 20
  34. 2021S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptationcited by 19
  35. 2021Active Learning for Deep Visual Trackingcited by 19
  36. 2021Boosting Active Learning via Improving Test Performancecited by 19
  37. 2021MCDAL: Maximum Classifier Discrepancy for Active Learningcited by 18
  38. 2022Learning Distinctive Margin toward Active Domain Adaptationcited by 18

50 most cited of 335 All 335 (JSON)