mlsanityData to 7 Oct 2026

Active Learning for Deep Object Detection

arXiv 1809.09875 ↗First posted 26 Sep 2018cs.CV cs.LGcited by 49

Not on the map. Why?

Abstract (arXiv)

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, when labeled, are expected to improve the model the most. In this paper, we combine a novel method of active learning for object detection with an incremental learning scheme to enable continuous exploration of new unlabeled datasets. We propose a set of uncertainty-based active learning metrics suitable for most object detectors. Furthermore, we present an approach to leverage class imbalances during sample selection. All methods are evaluated systematically in a continuous exploration context on the PASCAL VOC 2012 dataset.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 12; 2023: 14; 2024: 3; 2025: 8; 2026: 6.

49 papers.

Sort:

  1. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  2. 2024Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approachcited by 48
  3. 2022CitySim: A Drone-Based Vehicle Trajectory Dataset for Safety Oriented Research and Digital Twinscited by 43
  4. 2021A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyondcited by 37
  5. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  6. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  7. 2023Streaming Active Learning with Deep Neural Networkscited by 20
  8. 2022Active Learning Strategies for Weakly-supervised Object Detectioncited by 17
  9. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
  10. 2023Identifying Label Errors in Object Detection Datasets by Loss Inspectioncited by 16
  11. 2023Multi-Task Consistency for Active Learningcited by 9
  12. 2023Active Learning for Semantic Segmentation with Multi-class Label Querycited by 9
37 more
  1. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  2. 2021When Deep Learners Change Their Mind: Learning Dynamics for Active Learningcited by 6
  3. 2022ALBench: A Framework for Evaluating Active Learning in Object Detectioncited by 6
  4. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  5. 2024Inconsistency-Based Data-Centric Active Open-Set Annotationcited by 5
  6. 2023An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasetscited by 4
  7. 2022Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detectioncited by 3
  8. 2023Assessing Domain Gap for Continual Domain Adaptation in Object Detectioncited by 3
  9. 2023Active Learning for Object Detection with Non-Redundant Informative Samplingcited by 3
  10. 2021Region-level Active Detector Learningcited by 2
  11. 2023Deep Active Learning with Noisy Oracle in Object Detectioncited by 2
  12. 2025Streamlining the Development of Active Learning Methods in Real-World Object Detectioncited by 2
  13. 2022Evaluating Zero-cost Active Learning for Object Detectioncited by 1
  14. 2023Classification Committee for Active Deep Object Detectioncited by 1
  15. 2023Reinforcement-based Display-size Selection for Frugal Satellite Image Change Detectioncited by 1
  16. 2024Improved detection of discarded fish species through BoxAL active learningcited by 1
  17. 2025A model-agnostic active learning approach for animal detection from camera trapscited by 1
  18. 2025Table Detection with Active Learningcited by 1
  19. 2025On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Explorationcited by 1
  20. 2026Active Learning Strategies for Efficient Machine-Learned Interatomic Potentials Across Diverse Material Systemscited by 1
  21. 2026Portable Active Learning for Object Detectioncited by 1
  22. 2021OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysiscited by 0
  23. 2022An Iterative Labeling Method for Annotating Fisheries Imagerycited by 0
  24. 2022Confidence Estimation for Object Detection in Document Imagescited by 0
  25. 2022Frugal Reinforcement-based Active Learningcited by 0
  26. 2022Adversarial Virtual Exemplar Learning for Label-Frugal Satellite Image Change Detectioncited by 0
  27. 2023Uncertainty Aware Active Learning for Reconfiguration of Pre-trained Deep Object-Detection Networks for New Target Domainscited by 0
  28. 2023Frugal Satellite Image Change Detection with Deep-Net Inversioncited by 0
  29. 2023Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Samplingcited by 0
  30. 2025Box-Level Class-Balanced Sampling for Active Object Detectioncited by 0
  31. 2025Label-frugal satellite image change detection with generative virtual exemplar learningcited by 0
  32. 2025Sample-Centric Multi-Task Learning for Detection and Segmentation of Industrial Surface Defectscited by 0
  33. 2025Image augmentation with invertible networks in interactive satellite image change detectioncited by 0
  34. 2026RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagerycited by 0
  35. 2026ALINC: Active Learning for Inductive Node Classification via Graph Samplingcited by 0
  36. 2026Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Trackingcited by 0
  37. 2026Distance to Class Prototypes: Active Learning for Object Detectioncited by 0