2000 character limit reached
Verification for Object Detection -- IBP IoU (2403.08788v1)
Published 30 Jan 2024 in cs.CV, cs.AI, and cs.NE
Abstract: We introduce a novel Interval Bound Propagation (IBP) approach for the formal verification of object detection models, specifically targeting the Intersection over Union (IoU) metric. The approach has been implemented in an open source code, named IBP IoU, compatible with popular abstract interpretation based verification tools. The resulting verifier is evaluated on landing approach runway detection and handwritten digit recognition case studies. Comparisons against a baseline (Vanilla IBP IoU) highlight the superior performance of IBP IoU in ensuring accuracy and stability, contributing to more secure and robust machine learning applications.
- Certifying geometric robustness of neural networks. Advances in Neural Information Processing Systems, 32, 2019.
- Neural network based runway landing guidance for general aviation autoland. Technical report, United States. Department of Transportation. Federal Aviation Administration …, 2021.
- Lard–landing approach runway detection–dataset for vision based landing. arXiv preprint arXiv:2304.09938, 2023.
- Li Deng. The mnist database of handwritten digit images for machine learning research. IEEE Signal Processing Magazine, 29(6):141–142, 2012.
- Melanie Ducoffe. Decomon: Automatic certified perturbation analysis of neural networks. https://github.com/airbus/decomon. 2023-11-20.
- Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395, 1981.
- Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580–587, 2014.
- Evaluation of runtime monitoring for UAV emergency landing. In 2022 International Conference on Robotics and Automation, ICRA 2022, Philadelphia, PA, USA, May 23-27, 2022, pages 9703–9709. IEEE, 2022.
- On the effectiveness of interval bound propagation for training verifiably robust models. arXiv preprint arXiv:1810.12715, 2018.
- On the effectiveness of interval bound propagation for training verifiably robust models. arxiv 2018. arXiv preprint arXiv:1810.12715, 2018.
- Ai2: Safety and robustness certification of neural networks with abstract interpretation. In 2018 IEEE symposium on security and privacy (SP), pages 3–18. IEEE, 2018.
- Interval arithmetic: From principles to implementation. Journal of the ACM (JACM), 48(5):1038–1068, 2001.
- A review of yolo algorithm developments. Procedia Computer Science, 199:1066–1073, 2022.
- Verification of semantic key point detection for aircraft pose estimation. In Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning, volume 19, pages 757–762, 2023.
- Differentiable abstract interpretation for provably robust neural networks. In International Conference on Machine Learning, pages 3578–3586. PMLR, 2018.
- Scaling polyhedral neural network verification on gpus. Proceedings of Machine Learning and Systems, 3:733–746, 2021.
- U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234–241. Springer, 2015.
- Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 658–666, 2019.
- Teruo Sunaga et al. Theory of an interval algebra and its application to numerical analysis. Japan Journal of Industrial and Applied Mathematics, 26(2):125, 2009.
- Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9627–9636, 2019.
- Automatic perturbation analysis for scalable certified robustness and beyond. Advances in Neural Information Processing Systems, 33, 2020.
- Towards stable and efficient training of verifiably robust neural networks. arXiv preprint arXiv:1906.06316, 2019.
- Efficient neural network robustness certification with general activation functions. Advances in neural information processing systems, 31, 2018.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.