Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93190Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 徐宏民 | zh_TW |
| dc.contributor.advisor | Winston H. Hsu | en |
| dc.contributor.author | 陳皇宇 | zh_TW |
| dc.contributor.author | HUANG-YU CHEN | en |
| dc.date.accessioned | 2024-07-23T16:12:45Z | - |
| dc.date.available | 2024-07-24 | - |
| dc.date.copyright | 2024-07-23 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-17 | - |
| dc.identifier.citation | [1] S. Agarwal, H. Arora, S. Anand, and C. Arora. Contextual diversity for active learn ing. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVI 16, pages 137–153. Springer, 2020.
[2] J. Ash, S. Goel, A. Krishnamurthy, and S. Kakade. Gone fishing: Neural active learn ing with fisher embeddings. Advances in Neural Information Processing Systems, 34:8927–8939, 2021. [3] J. T. Ash, C. Zhang, A. Krishnamurthy, J. Langford, and A. Agarwal. Deep batch active learning by diverse, uncertain gradient lower bounds. In International Conference on Learning Representations, 2020. [4] A. Athar, E. Li, S. Casas, and R. Urtasun. 4dformer: Multimodal 4d panoptic seg mentation. In Conference on Robot Learning, pages 2151–2164. PMLR, 2023. [5] W. H. Beluch, T. Genewein, A. Nürnberger, and J. M. Köhler. The power of en sembles for active learning in image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 9368–9377, 2018. [6] J. W. Cho, D.J. Kim, Y. Jung, and I. S. Kweon. Mcdal: Maximum classifier dis crepancy for active learning. IEEE transactions on neural networks and learning systems, 2022 [7] J. Choi, I. Elezi, H.J. Lee, C. Farabet, and J. M. Alvarez. Active learning for deep object detection via probabilistic modeling. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10264–10273, 2021. [8] L. E. Dor, A. Halfon, A. Gera, E. Shnarch, L. Dankin, L. Choshen, M. Danilevsky, R. Aharonov, Y. Katz, and N. Slonim. Active learning for bert: an empirical study. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pages 7949–7962, 2020. [9] 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), pages 667–674. IEEE, 2019. [10] Y. Gal, R. Islam, and Z. Ghahramani. Deep bayesian active learning with image data. In International conference on machine learning, pages 1183–1192. PMLR, 2017. [11] 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, pages 3354–3361. IEEE, 2012. [12] A. Ghita, B. Antoniussen, W. Zimmer, R. Greer, C. Creß, A. Møgelmose, M. M. Trivedi, and A. C. Knoll. Activeanno3d–an active learning framework for multi modal 3d object detection. arXiv preprint arXiv:2402.03235, 2024. [13] A. Harakeh, M. Smart, and S. L. Waslander. Bayesod: A bayesian approach for un certainty estimation in deep object detectors. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 87–93. IEEE, 2020. [14] A. J. Joshi, F. Porikli, and N. Papanikolopoulos. Multiclass active learning for image classification. In 2009 ieee conference on computer vision and pattern recognition, pages 2372–2379. IEEE, 2009. [15] C.C. Kao, T.Y. Lee, P. Sen, and M.Y. Liu. Localizationaware active learning for object detection. In Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part VI 14, pages 506–522. Springer, 2019. [16] 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, pages 18279–18290, 2023. [17] Y. Luo, Z. Chen, Z. Wang, X. Yu, Z. Huang, and M. Baktashmotlagh. Explor ing active 3d object detection from a generalization perspective. In The Eleventh International Conference on Learning Representations, 2023. [18] J. Mao, Y. Xue, M. Niu, H. Bai, J. Feng, X. Liang, H. Xu, and C. Xu. Voxel transformer for 3d object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3164–3173, 2021. [19] D. Maturana and S. Scherer. Voxnet: A 3d convolutional neural network for real time object recognition. In 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS), pages 922–928. IEEE, 2015. [20] V. Nath, D. Yang, B. A. Landman, D. Xu, and H. R. Roth. Diminishing uncertainty within the training pool: Active learning for medical image segmentation. IEEE Transactions on Medical Imaging, 40(10):2534–2547, 2020. [21] Y. Park, W. Choi, S. Kim, D.J. Han, and J. Moon. Active learning for object detec tion with evidential deep learning and hierarchical uncertainty aggregation. In The Eleventh International Conference on Learning Representations, 2022. [22] Y. Park, J. Park, D.J. Han, W. Choi, H. Kousar, and J. Moon. Distribution aware active learning via gaussian mixtures. 2023. [23] A. Parvaneh, E. Abbasnejad, D. Teney, G. R. Haffari, A. Van Den Hengel, and J. Q. Shi. Active learning by feature mixing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12237–12246, 2022. [24] C. R. Qi, H. Su, K. Mo, and L. J. Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017. [25] C. R. Qi, L. Yi, H. Su, and L. J. Guibas. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30, 2017. [26] L. Qing, T. Wang, D. Lin, and J. Pang. Dort: Modeling dynamic objects in recurrent for multicamera 3d object detection and tracking. In Conference on Robot Learning, pages 3749–3765. PMLR, 2023. [27] S. Roy, A. Unmesh, and V. P. Namboodiri. Deep active learning for object detection. In BMVC, volume 362, page 91, 2018. [28] S. Schmidt, Q. Rao, J. Tatsch, and A. Knoll. Advanced active learning strategies for object detection. In 2020 IEEE intelligent vehicles symposium (IV), pages 871–876. IEEE, 2020. [29] D. W. Scott. Multivariate Density Estimation: Theory, Practice, and Visualization. Wiley, aug 1992. [30] O. Sener and S. Savarese. Active learning for convolutional neural networks: A coreset approach. In International Conference on Learning Representations, 2018. [31] B. Settles. Active learning literature survey. 2009. [32] S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang, and H. Li. Pvrcnn: Pointvoxel feature set abstraction for 3d object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10529–10538, 2020. [33] S. Shi, L. Jiang, J. Deng, Z. Wang, C. Guo, J. Shi, X. Wang, and H. Li. Pvrcnn++: Pointvoxel feature set abstraction with local vector representation for 3d object detection. International Journal of Computer Vision, 131(2):531–551, 2023. [34] Y. Siddiqui, J. Valentin, and M. Nießner. Viewal: Active learning with viewpoint entropy for semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9433–9443, 2020. [35] B. W. Silverman. Density estimation for statistics and data analysis. 1986. [36] P. Singhal, R. Walambe, S. Ramanna, and K. Kotecha. Domain adaptation: chal lenges, methods, datasets, and applications. IEEE access, 11:6973–7020, 2023. [37] P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V. Patnaik, P. Tsui, J. Guo, Y. Zhou, Y. Chai, B. Caine, et al. Scalability in perception for autonomous driv ing: Waymo open dataset. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2446–2454, 2020. [38] A. Tanwani. Dirl: Domaininvariant representation learning for simtoreal transfer. In Conference on Robot Learning, pages 1558–1571. PMLR, 2021. [39] L. Van der Maaten and G. Hinton. Visualizing data using tsne. Journal of machine learning research, 9(11), 2008. [40] C. Wang, C. Ma, M. Zhu, and X. Yang. Pointaugmenting: Crossmodal augmen tation for 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11794–11803, 2021. [41] D. Wang and Y. Shang. A new active labeling method for deep learning. In 2014 International joint conference on neural networks (IJCNN), pages 112–119. IEEE, 2014. [42] J. Wu, J. Chen, and D. Huang. Entropybased active learning for object detection with progressive diversity constraint. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9397–9406, 2022. [43] Y. Yan, Y. Mao, and B. Li. Second: Sparsely embedded convolutional detection. Sensors, 18(10):3337, 2018. [44] A. J. Yang, S. Casas, N. Dvornik, S. Segal, Y. Xiong, J. S. K. Hu, C. Fang, and R. Urtasun. Labelformer: Object trajectory refinement for offboard perception from lidar point clouds. In Conference on Robot Learning, pages 3364–3383. PMLR, 2023. [45] Yang, Chenhongyi and Huang, Lichao and Crowley, Elliot J. Plug and Play Active Learning for Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [46] D. Yoo and I. S. Kweon. Learning loss for active learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 93–102,2019. [47] T. Yuan, F. Wan, M. Fu, J. Liu, S. Xu, X. Ji, and Q. Ye. Multiple instance active learn ing for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5330–5339, 2021. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93190 | - |
| dc.description.abstract | 基於光學雷達的3D物體檢測是自動駕駛和機器人發展的關鍵技術。然而，資料標註的成本過高限制了其發展。我們提出一種新穎且有效的主動學習方法，名為分布差異與特徵異質性（DDFH），該方法同時考慮幾何特徵和模型嵌入，從實例層面和框架層面評估信息。分布差異評估未標記和已標記分布中實例的差異性和新穎性，使模型能夠在有限的數據下高效學習。特徵異質性確保框架內實例特徵的異質性，保持特徵多樣性，同時避免冗餘或相似實例，從而最小化標註成本。最後，使用分位數變換有效地聚合多個指標，提供一個統一的資訊量指標。廣泛的實驗表明，DDFH在KITTI和Waymo數據集上超越了當前最先進（SOTA）方法，有效地減少了標定框標註成本56.3％，並在單階段和雙階段的模型中展現出穩健性。 | zh_TW |
| dc.description.abstract | LiDAR-based 3D object detection is a critical technology for the development of autonomous driving and robotics. However, the high cost of data annotation limits its advancement. We propose a novel and effective active learning (AL) method called Distribution Discrepancy and Feature Heterogeneity (DDFH), which simultaneously considers geometric features and model embeddings, assessing information from both the instance-level and frame-level perspectives. Distribution Discrepancy evaluates the difference and novelty of instances within the unlabeled and labeled distributions, enabling the model to learn efficiently with limited data. Feature Heterogeneity ensures the heterogeneity of intra-frame instance features, maintaining feature diversity while avoiding redundant or similar instances, thus minimizing annotation costs. Finally, multiple indicators are efficiently aggregated using Quantile Transform, providing a unified measure of informativeness. Extensive experiments demonstrate that DDFH outperforms the current state-of-the-art (SOTA) methods on the KITTI and Waymo datasets, effectively reducing the bounding box annotation cost by 56.3% and showing robustness when working with both one-stage and two-stage models. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-23T16:12:45Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-23T16:12:45Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee | i
摘要 | iii Abstract | v Contents | vii List of Figures | ix List of Tables | xi Chapter 1 Introduction | 1 Chapter 2 Related Work | 5 2.1 LiDARbased 3D Object Detection | 5 2.2 Active learning for object detection | 6 Chapter 3 Methodology 7 3.1 Active Learning Setup | 7 3.2 Framework Overview | 7 3.2.1 Score Normalization | 8 3.3 InstanceLevel Distribution Discrepancy | 9 3.4 FrameLevel Feature Heterogeneity | 10 3.5 Confidence Balance for Imbalanced Data | 12 3.6 Acquisition Function | 13 Chapter 4 Experiment | 15 4.1 Experimental Settings | 15 4.1.1 3D Point Cloud Datasets | 15 4.1.2 Baselines | 15 4.1.3 Evaluation Metrics | 16 4.1.4 Implementation Details | 16 4.2 Main Results | 17 4.2.1 DDFH with TwoStage Detection Model | 17 4.2.2 DDFH with OneStage Detection Model | 18 4.3 Ablation Study | 19 4.3.1 Efficacy of Confidence Balance | 19 4.3.2 Efficacy of Distribution Discrepancy and Feature Heterogeneity | 19 4.3.3 Efficacy of Geometric Features | 19 Chapter 5 Conclusion | 21 References | 23 Appendix A — More Implementation Details 31 A.1 More Implementation Details | 31 Appendix B — More Experimental Details 33 B.1 DDFH in the KITTI Dataset | 34 B.2 Ablation Study of Density Estimation | 35 Appendix C — Limitation 37 C.1 Limitation | 37 | - |
| dc.language.iso | en | - |
| dc.subject | 主動學習 | zh_TW |
| dc.subject | 自動駕駛 | zh_TW |
| dc.subject | 光學雷達3D物件偵測 | zh_TW |
| dc.subject | Autonomous Driving | en |
| dc.subject | Active Learning | en |
| dc.subject | LiDAR 3D Object Detection | en |
| dc.title | 透過分佈差異和特徵異質性進行主動 3D 物體偵測 | zh_TW |
| dc.title | Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳文進;葉梅珍;鄭卜壬 | zh_TW |
| dc.contributor.oralexamcommittee | Wen-Chin Chen;Mei-Chen Yeh;Pu-Jen Cheng | en |
| dc.subject.keyword | 主動學習,光學雷達3D物件偵測,自動駕駛, | zh_TW |
| dc.subject.keyword | Active Learning,LiDAR 3D Object Detection,Autonomous Driving, | en |
| dc.relation.page | 37 | - |
| dc.identifier.doi | 10.6342/NTU202401627 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-07-18 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| Appears in Collections: | 資訊工程學系 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-112-2.pdf | 13.07 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.