mlsanityData to 7 Oct 2026

Localization-Aware Active Learning for Object Detection

arXiv 1801.05124 ↗First posted 16 Jan 2018cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Active learning - a class of algorithms that iteratively searches for the most informative samples to include in a training dataset - has been shown to be effective at annotating data for image classification. However, the use of active learning for object detection is still largely unexplored as determining informativeness of an object-location hypothesis is more difficult. In this paper, we address this issue and present two metrics for measuring the informativeness of an object hypothesis, which allow us to leverage active learning to reduce the amount of annotated data needed to achieve a target object detection performance. Our first metric measures 'localization tightness' of an object hypothesis, which is based on the overlapping ratio between the region proposal and the final prediction. Our second metric measures 'localization stability' of an object hypothesis, which is based on the variation of predicted object locations when input images are corrupted by noise. Our experimental results show that by augmenting a conventional active-learning algorithm designed for classification with the proposed metrics, the amount of labeled training data required can be reduced up to 25%. Moreover, on PASCAL 2007 and 2012 datasets our localization-stability method has an average relative improvement of 96.5% and 81.9% over the baseline method using classification only.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 13; 2024: 5; 2025: 5; 2026: 5.

48 papers.

Sort:

  1. 2021Influence Selection for Active Learningcited by 82
  2. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  3. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  4. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  5. 2021Consistency-based Active Learning for Object Detectioncited by 32
  6. 2021Multi-Anchor Active Domain Adaptation for Semantic Segmentationcited by 29
  7. 2021Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detectioncited by 27
  8. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  9. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  10. 2022Active Learning Strategies for Weakly-supervised Object Detectioncited by 17
  11. 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
  12. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
36 more
  1. 2022Active Pointly-Supervised Instance Segmentationcited by 15
  2. 2023Box-Level Active Detectioncited by 13
  3. 2023KECOR: Kernel Coding Rate Maximization for Active 3D Object Detectioncited by 13
  4. 2023Multi-Task Consistency for Active Learningcited by 9
  5. 2021Bayesian Active Learning for Sim-to-Real Robotic Perceptioncited by 8
  6. 2023ALWOD: Active Learning for Weakly-Supervised Object Detectioncited by 8
  7. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  8. 2024SSE: Multimodal Semantic Data Selection and Enrichment for Industrial-scale Data Assimilationcited by 7
  9. 2021Active Learning for Deep Neural Networks on Edge Devicescited by 6
  10. 2022ALBench: A Framework for Evaluating Active Learning in Object Detectioncited by 6
  11. 2023MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentationcited by 5
  12. 2021Active learning using weakly supervised signals for quality inspectioncited by 4
  13. 2022MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detectioncited by 3
  14. 2023Active Learning for Object Detection with Non-Redundant Informative Samplingcited by 3
  15. 2021Region-level Active Detector Learningcited by 2
  16. 2025Streamlining the Development of Active Learning Methods in Real-World Object Detectioncited by 2
  17. 2022Towards an Error-free Deep Occupancy Detector for Smart Camera Parking Systemcited by 1
  18. 2023Classification Committee for Active Deep Object Detectioncited by 1
  19. 2023DeLR: Active Learning for Detection with Decoupled Localization and Recognition Querycited by 1
  20. 2024Deep Active Learning: A Reality Checkcited by 1
  21. 2024Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detectioncited by 1
  22. 2024AL-GTD: Deep Active Learning for Gaze Target Detectioncited by 1
  23. 2024STONE: A Submodular Optimization Framework for Active 3D Object Detectioncited by 1
  24. 2025Inconsistency-based Active Learning for LiDAR Object Detectioncited by 1
  25. 2025Table Detection with Active Learningcited by 1
  26. 2026BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentationcited by 1
  27. 2023Uncertainty Aware Active Learning for Reconfiguration of Pre-trained Deep Object-Detection Networks for New Target Domainscited by 0
  28. 2023MuRAL: Multi-Scale Region-based Active Learning for Object Detectioncited by 0
  29. 2023Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Samplingcited by 0
  30. 2023Open-CRB: Towards Open World Active Learning for 3D Object Detectioncited by 0
  31. 2025HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detectioncited by 0
  32. 2025Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precisioncited by 0
  33. 2026Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Imagescited by 0
  34. 2026From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Reviewcited by 0
  35. 2026Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Trackingcited by 0
  36. 2026Distance to Class Prototypes: Active Learning for Object Detectioncited by 0