Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration (2401.16634v1)

Published 30 Jan 2024 in cs.CV and cs.LG

Abstract: Active learning strategies for 3D object detection in autonomous driving datasets may help to address challenges of data imbalance, redundancy, and high-dimensional data. We demonstrate the effectiveness of entropy querying to select informative samples, aiming to reduce annotation costs and improve model performance. We experiment using the BEVFusion model for 3D object detection on the nuScenes dataset, comparing active learning to random sampling and demonstrating that entropy querying outperforms in most cases. The method is particularly effective in reducing the performance gap between majority and minority classes. Class-specific analysis reveals efficient allocation of annotated resources for limited data budgets, emphasizing the importance of selecting diverse and informative data for model training. Our findings suggest that entropy querying is a promising strategy for selecting data that enhances model learning in resource-constrained environments.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. S. Wang, Y. Sun, Z. Wang, and M. Liu, “St-tracknet: A multiple-object tracking network using spatio-temporal information,” IEEE Transactions on Automation Science and Engineering, 2022.
  2. H. Cai, Z. Zhang, Z. Zhou, Z. Li, W. Ding, and J. Zhao, “Bevfusion4d: Learning lidar-camera fusion under bird’s-eye-view via cross-modality guidance and temporal aggregation,” arXiv preprint arXiv:2303.17099, 2023.
  3. Z. Liu, H. Tang, A. Amini, X. Yang, H. Mao, D. L. Rus, and S. Han, “Bevfusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation,” in 2023 IEEE international conference on robotics and automation (ICRA).   IEEE, 2023, pp. 2774–2781.
  4. Y. Chen, Z. Yu, Y. Chen, S. Lan, A. Anandkumar, J. Jia, and J. M. Alvarez, “Focalformer3d: focusing on hard instance for 3d object detection,” in Proceedings of the IEEE/CVF International Conference On Computer Vision, 2023, pp. 8394–8405.
  5. Y. Xie, C. Xu, M.-J. Rakotosaona, P. Rim, F. Tombari, K. Keutzer, M. Tomizuka, and W. Zhan, “Sparsefusion: Fusing multi-modal sparse representations for multi-sensor 3d object detection,” arXiv preprint arXiv:2304.14340, 2023.
  6. N. Kulkarni, A. Rangesh, J. Buck, J. Feltracco, M. M. Trivedi, N. Deo, R. Greer, S. Sarraf, and S. Sathyanarayana, “Create a large-scale video driving dataset with detailed attributes using amazon sagemaker ground truth: Lisa amazonmlsl vehicle attributes (lava) dataset,” AWS Machine Learning Blog, June 2021.
  7. R. Greer, L. Rakla, S. Desai, A. Alofi, A. Gopalkrishnan, and M. Trivedi, “Champ: Crowdsourced, history-based advisory of mapped pedestrians for safer driver assistance systems,” arXiv preprint arXiv:2301.05842, 2023.
  8. H. Gottschalk, M. Rottmann, and M. Saltagic, “Does redundancy in ai perception systems help to test for super-human automated driving performance?” arXiv preprint arXiv:2112.04758, 2021.
  9. D. Cohn, L. Atlas, and R. Ladner, “Improving generalization with active learning,” Machine learning, vol. 15, pp. 201–221, 1994.
  10. B. Pes, “Learning from high-dimensional biomedical datasets: the issue of class imbalance,” IEEE Access, vol. 8, pp. 13 527–13 540, 2020.
  11. H. B. Lee, T. Nam, E. Yang, and S. J. Hwang, “Meta dropout: Learning to perturb latent features for generalization,” in Eighth International Conference on Learning Representations, ICLR 2020.   International Conference on Learning Representations, 2020.
  12. H. X. Liu and S. Feng, “" curse of rarity" for autonomous vehicles,” arXiv preprint arXiv:2207.02749, 2022.
  13. H. Abualsaud, S. Liu, D. B. Lu, K. Situ, A. Rangesh, and M. M. Trivedi, “Laneaf: Robust multi-lane detection with affinity fields,” IEEE Robotics and Automation Letters, vol. 6, no. 4, pp. 7477–7484, 2021.
  14. E. Haussmann, M. Fenzi, K. Chitta, J. Ivanecky, H. Xu, D. Roy, A. Mittel, N. Koumchatzky, C. Farabet, and J. M. Alvarez, “Scalable active learning for object detection,” in 2020 IEEE Intelligent Vehicles Symposium (IV), 2020, pp. 1430–1435.
  15. R. Greer, J. Isa, N. Deo, A. Rangesh, and M. M. Trivedi, “On salience-sensitive sign classification in autonomous vehicle path planning: Experimental explorations with a novel dataset,” in 2022 Winter Conference on Applications of Computer Vision (WACV).
  16. R. Greer, A. Gopalkrishnan, N. Deo, A. Rangesh, and M. Trivedi, “Salient sign detection in safe autonomous driving: Ai which reasons over full visual context,” 27th International Technical Symposium on the Enhanced Safety of Vehicles (ESV), 2023.
  17. R. Greer, A. Gopalkrishnan, J. Landgren, L. Rakla, A. Gopalan, and M. Trivedi, “Robust traffic light detection using salience-sensitive loss: Computational framework and evaluations,” in 2023 IEEE Intelligent Vehicles Symposium (IV), 2023, pp. 1–7.
  18. S. Lefevre, A. Carvalho, and F. Borrelli, “A learning-based framework for velocity control in autonomous driving,” IEEE Transactions on Automation Science and Engineering, vol. 13, no. 1, pp. 32–42, 2015.
  19. R. Greer, N. Deo, and M. Trivedi, “Trajectory prediction in autonomous driving with a lane heading auxiliary loss,” IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 4907–4914, 2021.
  20. R. Greer, A. Gopalkrishnan, M. Keskar, and M. M. Trivedi, “Patterns of vehicle lights: Addressing complexities of camera-based vehicle light datasets and metrics,” Pattern Recognition Letters, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0167865524000047
  21. A. Doshi and M. M. Trivedi, “Examining the impact of driving style on the predictability and responsiveness of the driver: Real-world and simulator analysis,” in 2010 IEEE Intelligent Vehicles Symposium.   IEEE, 2010, pp. 232–237.
  22. A. Balachandran, M. Brown, S. M. Erlien, and J. C. Gerdes, “Predictive haptic feedback for obstacle avoidance based on model predictive control,” IEEE Transactions on Automation Science and Engineering, vol. 13, no. 1, pp. 26–31, 2015.
  23. W. Zimmer, A. Rangesh, and M. Trivedi, “3d bat: A semi-automatic, web-based 3d annotation toolbox for full-surround, multi-modal data streams,” in 2019 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2019, pp. 1816–1821.
  24. J. Lee, S. Walsh, A. Harakeh, and S. L. Waslander, “Leveraging pre-trained 3d object detection models for fast ground truth generation,” in 2018 21st International Conference on Intelligent Transportation Systems (ITSC).   IEEE, 2018, pp. 2504–2510.
  25. C. Liu, X. Qian, X. Qi, E. Y. Lam, S.-C. Tan, and N. Wong, “Map-gen: An automated 3d-box annotation flow with multimodal attention point generator,” in 2022 26th International Conference on Pattern Recognition (ICPR).   IEEE, 2022, pp. 1148–1155.
  26. R. Greer, L. Rakla, A. Gopalkrishnan, and M. Trivedi, “Multi-view ensemble learning with missing data: Computational framework and evaluations using novel data from the safe autonomous driving domain,” arXiv preprint arXiv:2301.12592, 2023.
  27. D. Feng, X. Wei, L. Rosenbaum, A. Maki, and K. Dietmayer, “Deep active learning for efficient training of a lidar 3d object detector,” in 2019 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2019, pp. 667–674.
  28. A. Moses, S. Jakkampudi, C. Danner, and D. Biega, “Localization-based active learning (local) for object detection in 3d point clouds,” in Geospatial Informatics XII, vol. 12099.   SPIE, 2022, pp. 44–58.
  29. Y. Luo, Z. Chen, Z. Fang, Z. Zhang, M. Baktashmotlagh, and Z. Huang, “Kecor: Kernel coding rate maximization for active 3d object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 18 279–18 290.
  30. A. Hekimoglu, P. Friedrich, W. Zimmer, M. Schmidt, A. Marcos-Ramiro, and A. Knoll, “Multi-task consistency for active learning,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 3415–3424.
  31. A. Hekimoglu, M. Schmidt, and A. Marcos-Ramiro, “Monocular 3d object detection with lidar guided semi supervised active learning,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 2346–2355.
  32. S. Hwang, S. Kim, Y. Kim, and D. Kum, “Joint semi-supervised and active learning via 3d consistency for 3d object detection,” in 2023 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2023, pp. 4819–4825.
  33. S. Schmidt, Q. Rao, J. Tatsch, and A. Knoll, “Advanced active learning strategies for object detection,” in 2020 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2020, pp. 871–876.
  34. J. Yuan, B. Zhang, X. Yan, T. Chen, B. Shi, Y. Li, and Y. Qiao, “Bi3d: Bi-domain active learning for cross-domain 3d object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15 599–15 608.
  35. M. Meyer and G. Kuschk, “Automotive radar dataset for deep learning based 3d object detection,” in 2019 16th european radar conference (EuRAD).   IEEE, 2019, pp. 129–132.
  36. Q. Meng, W. Wang, T. Zhou, J. Shen, Y. Jia, and L. Van Gool, “Towards a weakly supervised framework for 3d point cloud object detection and annotation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 8, pp. 4454–4468, 2021.
  37. G. Villalonga and A. M. L. Pena, “Co-training for on-board deep object detection,” IEEE Access, vol. 8, pp. 194 441–194 456, 2020.
  38. A. Almin, L. Lemarié, A. Duong, and B. R. Kiran, “Navya3dseg-navya 3d semantic segmentation dataset design & split generation for autonomous vehicles,” IEEE Robotics and Automation Letters, 2023.
  39. O. Çatal, S. Leroux, C. De Boom, T. Verbelen, and B. Dhoedt, “Anomaly detection for autonomous guided vehicles using bayesian surprise,” in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2020, pp. 8148–8153.
  40. L. Chen, X. He, X. Zhao, H. Li, Y. Huang, B. Zhou, W. Chen, Y. Li, C. Wen, and C. Wang, “Gocomfort: Comfortable navigation for autonomous vehicles leveraging high-precision road damage crowdsensing,” IEEE Transactions on Mobile Computing, 2022.
  41. Z. Liang, X. Xu, S. Deng, L. Cai, T. Jiang, and K. Jia, “Exploring diversity-based active learning for 3d object detection in autonomous driving,” arXiv preprint arXiv:2205.07708, 2022.
  42. H. S. Seung, M. Opper, and H. Sompolinsky, “Query by committee,” in Proceedings of the fifth annual workshop on Computational learning theory, 1992, pp. 287–294.
  43. D. D. Lewis and J. Catlett, “Heterogeneous uncertainty sampling for supervised learning,” in Machine learning proceedings 1994.   Elsevier, 1994, pp. 148–156.
  44. T. Scheffer, C. Decomain, and S. Wrobel, “Active hidden markov models for information extraction,” in International Symposium on Intelligent Data Analysis.   Springer, 2001, pp. 309–318.
  45. B. Settles, M. Craven, and S. Ray, “Multiple-instance active learning,” Advances in neural information processing systems, vol. 20, pp. 1289–1296, 2007.
  46. A. I. Schein and L. H. Ungar, “Active learning for logistic regression: an evaluation,” Machine Learning, vol. 68, no. 3, pp. 235–265, 2007.
  47. B. Settles and M. Craven, “An analysis of active learning strategies for sequence labeling tasks,” in Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, 2008, pp. 1070–1079.
  48. S. Sivaraman and M. M. Trivedi, “A general active-learning framework for on-road vehicle recognition and tracking,” IEEE Transactions on Intelligent Transportation Systems, vol. 11, no. 2, pp. 267–276, 2010.
  49. ——, “Active learning for on-road vehicle detection: A comparative study,” Machine vision and applications, vol. 25, no. 3, pp. 599–611, 2014.
  50. R. K. Satzoda and M. M. Trivedi, “Multipart vehicle detection using symmetry-derived analysis and active learning,” IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 4, pp. 926–937, 2015.
  51. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Advances in neural information processing systems, vol. 25, pp. 1097–1105, 2012.
  52. N. Singh, H. Hukkelås, and F. Lindseth, “Deep active learning for autonomous perception,” in NIKT: Norsk IKT-konferanse for forskning og utdanning 2020.   Bibsys Open Journal Systems, 2020.
  53. A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? the kitti vision benchmark suite,” in 2012 IEEE conference on computer vision and pattern recognition.   IEEE, 2012, pp. 3354–3361.
  54. A. Hekimoglu, M. Schmidt, A. Marcos-Ramiro, and G. Rigoll, “Efficient active learning strategies for monocular 3d object detection,” in 2022 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2022, pp. 295–302.
  55. H. Caesar, V. Bankiti, A. H. Lang, S. Vora, V. E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, and O. Beijbom, “nuscenes: A multimodal dataset for autonomous driving,” CoRR, vol. abs/1903.11027, 2019. [Online]. Available: http://arxiv.org/abs/1903.11027
  56. A. Møgelmose, M. M. Trivedi, and T. B. Moeslund, “Trajectory analysis and prediction for improved pedestrian safety: Integrated framework and evaluations,” in 2015 IEEE intelligent vehicles symposium (IV).   IEEE, 2015, pp. 330–335.
  57. C. Finn, K. Xu, and S. Levine, “Probabilistic model-agnostic meta-learning,” Advances in neural information processing systems, vol. 31, 2018.
  58. D. D. Lewis and W. A. Gale, “A sequential algorithm for training text classifiers,” in SIGIR’94.   Springer, 1994, pp. 3–12.
  59. V. Nguyen, M. H. Shaker, and E. Hüllermeier, “How to measure uncertainty in uncertainty sampling for active learning,” https://doi.org/10.1007/s10994-021-06003-9, 2021.
  60. Z. Liu, H. Tang, A. Amini, X. Yang, H. Mao, D. Rus, and S. Han, “Bevfusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation,” arXiv preprint arXiv:2205.13542v2, 2022.
  61. Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, , and B. Guo, “Swin transformer: Hierarchical vision transformer using shifted window,” ICCV, 2021.
  62. Y. Yan, Y. Mao, , and B. Li, “Second: Sparsely embedded convolutional detection,” Sensors, 2018.
  63. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detectio,” CVPR, 2017.
  64. M. Fang, Y. Li, and T. Cohn, “Learning how to active learn: A deep reinforcement learning approach,” arXiv preprint arXiv:1708.02383, 2017.
  65. T. Lew, A. Sharma, J. Harrison, A. Bylard, and M. Pavone, “Safe active dynamics learning and control: A sequential exploration–exploitation framework,” IEEE Transactions on Robotics, vol. 38, no. 5, pp. 2888–2907, 2022.
  66. C. S. Vallon and F. Borrelli, “Data-driven strategies for hierarchical predictive control in unknown environments,” IEEE Transactions on Automation Science and Engineering, vol. 19, no. 3, pp. 1434–1445, 2022.
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets