VerifIoU -- Robustness of Object Detection to Perturbations
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 30 Jan 2024.
Builds on
15 of 31 references.
References · 15
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
- 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
- 2016Safety Verification of Deep Neural Networkscited by 263
- 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
- 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
- 2016Measuring Neural Net Robustness with Constraintscited by 90
- 2021Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Boundscited by 65
- 2020Scaling Polyhedral Neural Network Verification on GPUscited by 43
Built on by
Citing papers per year: 2026: 3.
3 papers.