mlsanityData to 14 Oct 2026

Multiple instance active learning for object detection

arXiv 2104.02324 ↗First posted 6 Apr 2021cs.CV cs.AI cs.LGcited by 77

Not on the map. Why?

Abstract (arXiv)

Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper, we propose Multiple Instance Active Object Detection (MI-AOD), to select the most informative images for detector training by observing instance-level uncertainty. MI-AOD defines an instance uncertainty learning module, which leverages the discrepancy of two adversarial instance classifiers trained on the labeled set to predict instance uncertainty of the unlabeled set. MI-AOD treats unlabeled images as instance bags and feature anchors in images as instances, and estimates the image uncertainty by re-weighting instances in a multiple instance learning (MIL) fashion. Iterative instance uncertainty learning and re-weighting facilitate suppressing noisy instances, toward bridging the gap between instance uncertainty and image-level uncertainty. Experiments validate that MI-AOD sets a solid baseline for instance-level active learning. On commonly used object detection datasets, MI-AOD outperforms state-of-the-art methods with significant margins, particularly when the labeled sets are small. Code is available at https://github.com/yuantn/MI-AOD.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). Builds on 17 of its 46 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

17 of 46 references.

References · 17

  1. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  2. 2017Deep Bayesian Active Learning with Image Datacited by 819
  3. 2019Learning Loss for Active Learningcited by 336
  4. 2019Variational Adversarial Active Learningcited by 284
  5. 2015Weakly Supervised Deep Detection Networkscited by 183
  6. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  7. 2020Contextual Diversity for Active Learningcited by 139
  8. 2019FreeAnchor: Learning to Match Anchors for Visual Object Detectioncited by 90
  9. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  10. 2019Active Learning for Deep Detection Neural Networkscited by 62
  11. 2020State-Relabeling Adversarial Active Learningcited by 60
  12. 2019Min-Entropy Latent Model for Weakly Supervised Object Detectioncited by 45
5 more
  1. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  2. 2015Hierarchical Subquery Evaluation for Active Learning on a Graphcited by 21
  3. 2017Active Self-Paced Learning for Cost-Effective and Progressive Face Identificationcited by 19
  4. 2016Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changescited by 18
  5. 2017Bag-Level Aggregation for Multiple Instance Active Learning in Instance Classification Problemscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 16; 2023: 26; 2024: 10; 2025: 15; 2026: 6.

77 papers.

Sort:

By area:

  1. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
  2. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 54
  3. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  4. 2023Active Teacher for Semi-Supervised Object Detectioncited by 43
  5. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  6. 2023A comprehensive survey on deep active learning in medical image analysiscited by 35
  7. 2022Plug and Play Active Learning for Object Detectioncited by 28
  8. 2021Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detectioncited by 27
  9. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  10. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
  11. 2023Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detectioncited by 22
  12. 2024Coreset Selection for Object Detectioncited by 18
38 more
  1. 2022Active Learning Strategies for Weakly-supervised Object Detectioncited by 17
  2. 2022Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoningcited by 16
  3. 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
  4. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
  5. 2022Active Pointly-Supervised Instance Segmentationcited by 15
  6. 2023Box-Level Active Detectioncited by 13
  7. 2023KECOR: Kernel Coding Rate Maximization for Active 3D Object Detectioncited by 13
  8. 2023Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learningcited by 10
  9. 2023Towards Free Data Selection with General-Purpose Modelscited by 10
  10. 2023Towards Balanced Active Learning for Multimodal Classificationcited by 9
  11. 2023Multi-Task Consistency for Active Learningcited by 9
  12. 2024YOLO-UniOW: Efficient Universal Open-World Object Detectioncited by 9
  13. 2023ALWOD: Active Learning for Weakly-Supervised Object Detectioncited by 8
  14. 2022ALBench: A Framework for Evaluating Active Learning in Object Detectioncited by 7
  15. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  16. 2024ACTRESS: Active Retraining for Semi-supervised Visual Groundingcited by 7
  17. 2025Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detectioncited by 7
  18. 2021CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentationcited by 6
  19. 2021Towards General and Efficient Active Learningcited by 6
  20. 2025Multi-Instance Partial-Label Learning with Margin Adjustmentcited by 5
  21. 2022Fine-Grained Visual Entailmentcited by 4
  22. 2022Efficient Human-in-the-loop System for Guiding DNNs Attentioncited by 4
  23. 2023ReBound: An Open-Source 3D Bounding Box Annotation Tool for Active Learningcited by 4
  24. 2023An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasetscited by 4
  25. 2023Active Learning for Object Detection with Non-Redundant Informative Samplingcited by 4
  26. 2022Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detectioncited by 3
  27. 2023Assessing Domain Gap for Continual Domain Adaptation in Object Detectioncited by 3
  28. 2023REAL: A Representative Error-Driven Approach for Active Learningcited by 3
  29. 2023Learning to Rank for Active Learning via Multi-Task Bilevel Optimizationcited by 3
  30. 2025OmViD: Omni-supervised active learning for video action detectioncited by 3
  31. 2025Streamlining the Development of Active Learning Methods in Real-World Object Detectioncited by 3
  32. 2022Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detectioncited by 2
  33. 2023DeLR: Active Learning for Detection with Decoupled Localization and Recognition Querycited by 2
  34. 2024VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awarenesscited by 2
  35. 2024Boosting Semi-Supervised Object Detection in Remote Sensing Images With Active Teachingcited by 2
  36. 2025Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasetscited by 2
  37. 20253DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentationcited by 2
  38. 2025IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detectioncited by 2

50 most cited of 77 All 77 (JSON)