mlsanityData to 7 Oct 2026

Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint

arXiv 2204.07965 ↗First posted 17 Apr 2022cs.CVcited by 53

Not on the map. Why?

Abstract (arXiv)

Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label. Active learning for object detection is more challenging and existing efforts on it are relatively rare. In this paper, we propose a novel hybrid approach to address this problem, where the instance-level uncertainty and diversity are jointly considered in a bottom-up manner. To balance the computational complexity, the proposed approach is designed as a two-stage procedure. At the first stage, an Entropy-based Non-Maximum Suppression (ENMS) is presented to estimate the uncertainty of every image, which performs NMS according to the entropy in the feature space to remove predictions with redundant information gains. At the second stage, a diverse prototype (DivProto) strategy is explored to ensure the diversity across images by progressively converting it into the intra-class and inter-class diversities of the entropy-based class-specific prototypes. Extensive experiments are conducted on MS COCO and Pascal VOC, and the proposed approach achieves state of the art results and significantly outperforms the other counterparts, highlighting its superiority.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 17 Apr 2022.

Builds on

25 of 42 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2015Fast R-CNNcited by 2,930
  10. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  11. 2017Deep Bayesian Active Learning with Image Datacited by 812
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
13 more
  1. 2019Learning Loss for Active Learningcited by 335
  2. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  3. 2019Variational Adversarial Active Learningcited by 284
  4. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
  5. 2020Contextual Diversity for Active Learningcited by 139
  6. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  7. 2020Cross-domain Object Detection through Coarse-to-Fine Feature Adaptationcited by 82
  8. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  9. 2021Multiple instance active learning for object detectioncited by 77
  10. 2020State-Relabeling Adversarial Active Learningcited by 60
  11. 2018Active Learning for Deep Object Detectioncited by 49
  12. 2018Localization-Aware Active Learning for Object Detectioncited by 48
  13. 2018Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detectioncited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 15; 2024: 8; 2025: 15; 2026: 10.

53 papers.

Sort:

By area:

  1. 2022PROB: Probabilistic Objectness for Open World Object Detectioncited by 57
  2. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  3. 2023Feedback-guided Data Synthesis for Imbalanced Classificationcited by 33
  4. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  5. 2023Active learning for data streams: a surveycited by 29
  6. 2022Plug and Play Active Learning for Object Detectioncited by 28
  7. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  8. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
  9. 2023Box-Level Active Detectioncited by 13
  10. 2023KECOR: Kernel Coding Rate Maximization for Active 3D Object Detectioncited by 13
  11. 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environmentscited by 11
  12. 2024Breaking the Barrier: Selective Uncertainty-based Active Learning for Medical Image Segmentationcited by 9
38 more
  1. 2023ALWOD: Active Learning for Weakly-Supervised Object Detectioncited by 8
  2. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  3. 2025Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detectioncited by 7
  4. 2025Active Test-time Vision-Language Navigationcited by 7
  5. 2022A Survey of Dataset Refinement for Problems in Computer Vision Datasetscited by 5
  6. 2024Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrievalcited by 5
  7. 2024Understanding Uncertainty-based Active Learning Under Model Mismatchcited by 3
  8. 2023Robust Assignment of Labels for Active Learning with Sparse and Noisy Annotationscited by 2
  9. 2023A Pre-trained Data Deduplication Model based on Active Learningcited by 2
  10. 2025StepAL: Step-aware Active Learning for Cataract Surgical Videoscited by 2
  11. 2025Streamlining the Development of Active Learning Methods in Real-World Object Detectioncited by 2
  12. 2023IAdet: Simplest human-in-the-loop object detectioncited by 1
  13. 2023Classification Committee for Active Deep Object Detectioncited by 1
  14. 2024Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detectioncited by 1
  15. 2024AL-GTD: Deep Active Learning for Gaze Target Detectioncited by 1
  16. 2025Inconsistency-based Active Learning for LiDAR Object Detectioncited 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. 2026Performance-guided Reinforced Active Learning for Object Detectioncited by 1
  20. 2026Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Imagescited by 1
  21. 2026Portable Active Learning for Object Detectioncited by 1
  22. 2023MuRAL: Multi-Scale Region-based Active Learning for Object Detectioncited by 0
  23. 2023Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Samplingcited by 0
  24. 2023Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detectioncited by 0
  25. 2023Open-CRB: Towards Open World Active Learning for 3D Object Detectioncited by 0
  26. 2024Salutary Labeling with Zero Human Annotationcited by 0
  27. 2024TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detectioncited by 0
  28. 2025Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detectioncited by 0
  29. 2025HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detectioncited by 0
  30. 2025Cost-effective Reduced-Order Modeling via Bayesian Active Learningcited by 0
  31. 2025Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibrationcited by 0
  32. 2025Box-Level Class-Balanced Sampling for Active Object Detectioncited by 0
  33. 2025Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deploymentcited by 0
  34. 2025Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precisioncited by 0
  35. 2026ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Predictioncited by 0
  36. 2026Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomenacited by 0
  37. 2026Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learningcited by 0
  38. 2026Foundation-Assisted Active Learning for Object Detection Annotationcited by 0

50 most cited of 53 All 53 (JSON)