Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection (2404.15879v1)

Published 24 Apr 2024 in cs.CV and cs.LG

Abstract: LiDAR-based 3D object detection has become an essential part of automated driving due to its ability to localize and classify objects precisely in 3D. However, object detectors face a critical challenge when dealing with unknown foreground objects, particularly those that were not present in their original training data. These out-of-distribution (OOD) objects can lead to misclassifications, posing a significant risk to the safety and reliability of automated vehicles. Currently, LiDAR-based OOD object detection has not been well studied. We address this problem by generating synthetic training data for OOD objects by perturbing known object categories. Our idea is that these synthetic OOD objects produce different responses in the feature map of an object detector compared to in-distribution (ID) objects. We then extract features using a pre-trained and fixed object detector and train a simple multilayer perceptron (MLP) to classify each detection as either ID or OOD. In addition, we propose a new evaluation protocol that allows the use of existing datasets without modifying the point cloud, ensuring a more authentic evaluation of real-world scenarios. The effectiveness of our method is validated through experiments on the newly proposed nuScenes OOD benchmark. The source code is available at https://github.com/uulm-mrm/mmood3d.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. D. Feng, C. Haase-Schütz, L. Rosenbaum, H. Hertlein, C. Gläser, F. Timm, W. Wiesbeck, and K. Dietmayer, “Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 3, pp. 1341–1360, 2021.
  2. A. Nguyen, J. Yosinski, and J. Clune, “Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2015, pp. 427–436.
  3. D. Hendrycks and K. Gimpel, “A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks,” in Int. Conf. Learn. Represent., 2017.
  4. S. Liang, Y. Li, and R. Srikant, “Enhancing the Reliability of Out-of-Distribution Image Detection in Neural Networks,” in Int. Conf. Learn. Represent., 2018.
  5. D. Hendrycks, S. Basart, M. Mazeika, M. Mostajabi, J. Steinhardt, and D. X. Song, “Scaling Out-of-Distribution Detection for Real-World Settings,” in Int. Conf. Mach. Learn., 2022.
  6. W. Liu, X. Wang, J. Owens, and Y. Li, “Energy-Based Out-of-Distribution Detection,” Adv. Neural Inf. Process. Syst., vol. 33, pp. 21 464–21 475, 2020.
  7. X. Du, Z. Wang, M. Cai, and Y. Li, “VOS: Learning What You Don’t Know by Virtual Outlier Synthesis,” in Int. Conf. Learn. Represent., 2022.
  8. S. Wilson, T. Fischer, F. Dayoub, D. Miller, and N. Sünderhauf, “SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection,” in Proc. Int. Conf. Comput. Vis., October 2023, pp. 23 565–23 576.
  9. A. Wu, D. Chen, and C. Deng, “Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution Objects,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2023, pp. 13 381–13 391.
  10. N. Kumar, S. Šegvić, A. Eslami, and S. Gumhold, “Normalizing Flow Based Feature Synthesis for Outlier-Aware Object Detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2023, pp. 5156–5165.
  11. C. Huang, V. Abdelzad, C. G. Mannes, L. Rowe, B. Therien, R. Salay, K. Czarnecki et al., “Out-of-Distribution Detection for LiDAR-Based 3D Object Detection,” in Int. Conf. Intell. Transp. Syst.   IEEE, 2022, pp. 4265–4271.
  12. B. Schölkopf, R. C. Williamson, A. Smola, J. Shawe-Taylor, and J. Platt, “Support Vector Method for Novelty Detection,” Adv. Neural Inf. Process. Syst., vol. 12, 1999.
  13. L. Dinh, J. Sohl-Dickstein, and S. Bengio, “Density Estimation Using Real NVP,” in Int. Conf. Learn. Represent., 2017.
  14. 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,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2020, pp. 11 621–11 631.
  15. C. R. Qi, H. Su, K. Mo, and L. J. Guibas, “PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2017, pp. 652–660.
  16. C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space,” Adv. Neural Inf. Process. Syst., vol. 30, 2017.
  17. Y. Zhou and O. Tuzel, “VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2018, pp. 4490–4499.
  18. Y. Yan, Y. Mao, and B. Li, “SECOND: Sparsely Embedded Convolutional Detection,” Sensors, vol. 18, no. 10, p. 3337, 2018.
  19. A. H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, and O. Beijbom, “PointPillars: Fast Encoders for Object Detection from Point Clouds,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2019, pp. 12 697–12 705.
  20. T. Yin, X. Zhou, and P. Krahenbuhl, “Center-Based 3D Object Detection and Tracking,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2021, pp. 11 784–11 793.
  21. D. Hendrycks, M. Mazeika, and T. Dietterich, “Deep Anomaly Detection with Outlier Exposure,” in Int. Conf. Learn. Represent., 2019.
  22. J. Hornauer and V. Belagiannis, “Heatmap-Based Out-of-Distribution Detection,” in Proc. IEEE Winter Conf. Appl. Comput. Vis., 2023, pp. 2603–2612.
  23. K. Lee, K. Lee, H. Lee, and J. Shin, “A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks,” Adv. Neural Inf. Process. Syst., vol. 31, 2018.
  24. A. Piroli, V. Dallabetta, J. Kopp, M. Walessa, D. Meissner, and K. Dietmayer, “LS-VOS: Identifying Outliers in 3D Object Detections Using Latent Space Virtual Outlier Synthesis,” in Int. Conf. Intell. Transp. Syst., 2023, pp. 1242–1248.
  25. J. Cen, P. Yun, S. Zhang, J. Cai, D. Luan, M. Tang, M. Liu, and M. Yu Wang, “Open-World Semantic Segmentation for LIDAR Point Clouds,” in Eur. Conf. Comput. Vis.   Springer, 2022, pp. 318–334.
  26. K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” in Proc. Int. Conf. Comput. Vis., 2017, pp. 2961–2969.
  27. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2014, pp. 580–587.
  28. A. Dosovitskiy, G. Ros, F. Codevilla, A. Lopez, and V. Koltun, “CARLA: An Open Urban Driving Simulator,” in Conf. on Robot Learning.   PMLR, 2017, pp. 1–16.
  29. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” Adv. Neural Inf. Process. Syst., vol. 32, 2019.
  30. M. Contributors, “MMDetection3D: OpenMMLab next-generation platform for general 3D object detection,” https://github.com/open-mmlab/mmdetection3d, 2020.
  31. I. Sutskever, J. Martens, G. Dahl, and G. Hinton, “On the Importance of Initialization and Momentum in Deep Learning,” in Int. Conf. Mach. Learn.   PMLR, 2013, pp. 1139–1147.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Michael Kösel (1 paper)
  2. Marcel Schreiber (5 papers)
  3. Michael Ulrich (10 papers)
  4. Claudius Gläser (17 papers)
  5. Klaus Dietmayer (106 papers)
Citations (2)
View on Semantic Scholar

Summary

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

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