mlsanityData to 14 Oct 2026

Active Learning for Deep Detection Neural Networks

arXiv 1911.09168 ↗First posted 20 Nov 2019cs.CV cs.LGcited by 62

Not on the map. Why?

Abstract (arXiv)

The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of labeling by selecting only those images that are informative to improve the detection network accuracy. In this paper, we propose a method to perform active learning of object detectors based on convolutional neural networks. We propose a new image-level scoring process to rank unlabeled images for their automatic selection, which clearly outperforms classical scores. The proposed method can be applied to videos and sets of still images. In the former case, temporal selection rules can complement our scoring process. As a relevant use case, we extensively study the performance of our method on the task of pedestrian detection. Overall, the experiments show that the proposed method performs better than random selection. Our codes are publicly available at www.gitlab.com/haghdam/deep_active_learning.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 16; 2023: 16; 2024: 6; 2025: 1; 2026: 4.

62 papers.

Sort:

By area:

  1. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  2. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 167
  3. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 113
  4. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  5. 2021Multiple instance active learning for object detectioncited by 77
  6. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  7. 2024Technical Report on the Pangram AI-Generated Text Classifiercited by 34
  8. 2022Discovering and forecasting extreme events via active learning in neural operatorscited by 32
  9. 2021Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detectioncited by 27
  10. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  11. 2021Active Learning for Deep Visual Trackingcited by 19
  12. 2021MCDAL: Maximum Classifier Discrepancy for Active Learningcited by 18
38 more
  1. 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
  2. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
  3. 2022Active Pointly-Supervised Instance Segmentationcited by 15
  4. 2023Neural Interactive Keypoint Detectioncited by 12
  5. 2023Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learningcited by 10
  6. 2023Multi-Task Consistency for Active Learningcited by 9
  7. 2021Bayesian Active Learning for Sim-to-Real Robotic Perceptioncited by 8
  8. 2021Active learning with MaskAL reduces annotation effort for training Mask R-CNNcited by 7
  9. 2022ALBench: A Framework for Evaluating Active Learning in Object Detectioncited by 7
  10. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  11. 2021When Deep Learners Change Their Mind: Learning Dynamics for Active Learningcited by 6
  12. 2021CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentationcited by 6
  13. 2021Active Learning of Neural Collision Handler for Complex 3D Mesh Deformationscited by 5
  14. 2021YMIR: A Rapid Data-centric Development Platform for Vision Applicationscited by 5
  15. 2021Deep Unsupervised Active Learning on Learnable Graphscited by 4
  16. 2023Active Learning for Object Detection with Non-Redundant Informative Samplingcited by 4
  17. 2021Dataset Definition Standard (DDS)cited by 3
  18. 2022MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detectioncited by 3
  19. 2023Spectral Transfer Guided Active Domain Adaptation For Thermal Imagerycited by 3
  20. 2023Automated Detection of Cat Facial Landmarkscited by 3
  21. 2025OmViD: Omni-supervised active learning for video action detectioncited by 3
  22. 2026Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysiscited by 3
  23. 2021Region-level Active Detector Learningcited by 2
  24. 2022LiDAR dataset distillation within bayesian active learning framework: Understanding the effect of data augmentationcited by 2
  25. 2022Suggestive Annotation of Brain MR Images with Gradient-guided Samplingcited by 2
  26. 2022Query-based Hard-Image Retrieval for Object Detection at Test Timecited by 2
  27. 2022Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detectioncited by 2
  28. 2023A Pre-trained Data Deduplication Model based on Active Learningcited by 2
  29. 2023DeLR: Active Learning for Detection with Decoupled Localization and Recognition Querycited by 2
  30. 2024Domain Adversarial Active Learning for Domain Generalization Classificationcited by 2
  31. 2026Performance-guided Reinforced Active Learning for Object Detectioncited by 2
  32. 2026Learning to Select Like Humans: Explainable Active Learning for Medical Imagingcited by 2
  33. 2022Towards an Error-free Deep Occupancy Detector for Smart Camera Parking Systemcited by 1
  34. 2022Virtual Reality via Object Pose Estimation and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilitiescited by 1
  35. 2023Deep active learning for nonlinear system identificationcited by 1
  36. 2023Classification Committee for Active Deep Object Detectioncited by 1
  37. 2024Deep Active Learning: A Reality Checkcited by 1
  38. 2024AL-GTD: Deep Active Learning for Gaze Target Detectioncited by 1

50 most cited of 62 All 62 (JSON)