Copula-based conformal prediction for object detection: a more efficient approach

Bruce Cyusa Mukama, Soundouss Messoudi, Sylvain Rousseau, Sébastien Destercke
Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 230:140-157, 2024.

Abstract

Object detection is an important vision task, and providing statistical guarantees around such detections can be of critical importance. So far, most conformal bounding box regression approaches do not simultaneously account for heteroscedasticity and dependencies between the residuals of each dimension. In this paper, we examine the importance of such dependencies and heteroscedasticity in the context of multi-target conformal regression, we apply copula-based conformal prediction methods to model them and to improve the volume of bounding box prediction regions. We compare these methods to the state-of-the-art conformal object detection approaches (on the KITTI & the BDD100K autonomous driving benchmarks) and the empirical copula-based method shows high-efficiency results that are robust w.r.t. heteroscedasticity and also robust w.r.t. the structure of the dependencies.

Cite this Paper

BibTeX
@InProceedings{pmlr-v230-mukama24a, title = {Copula-based conformal prediction for object detection: a more efficient approach}, author = {Mukama, Bruce Cyusa and Messoudi, Soundouss and Rousseau, Sylvain and Destercke, S\'{e}bastien}, booktitle = {Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {140--157}, year = {2024}, editor = {Vantini, Simone and Fontana, Matteo and Solari, Aldo and Boström, Henrik and Carlsson, Lars}, volume = {230}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v230/main/assets/mukama24a/mukama24a.pdf}, url = {https://proceedings.mlr.press/v230/mukama24a.html}, abstract = {Object detection is an important vision task, and providing statistical guarantees around such detections can be of critical importance. So far, most conformal bounding box regression approaches do not simultaneously account for heteroscedasticity and dependencies between the residuals of each dimension. In this paper, we examine the importance of such dependencies and heteroscedasticity in the context of multi-target conformal regression, we apply copula-based conformal prediction methods to model them and to improve the volume of bounding box prediction regions. We compare these methods to the state-of-the-art conformal object detection approaches (on the KITTI & the BDD100K autonomous driving benchmarks) and the empirical copula-based method shows high-efficiency results that are robust w.r.t. heteroscedasticity and also robust w.r.t. the structure of the dependencies.} }
Endnote
%0 Conference Paper %T Copula-based conformal prediction for object detection: a more efficient approach %A Bruce Cyusa Mukama %A Soundouss Messoudi %A Sylvain Rousseau %A Sébastien Destercke %B Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2024 %E Simone Vantini %E Matteo Fontana %E Aldo Solari %E Henrik Boström %E Lars Carlsson %F pmlr-v230-mukama24a %I PMLR %P 140--157 %U https://proceedings.mlr.press/v230/mukama24a.html %V 230 %X Object detection is an important vision task, and providing statistical guarantees around such detections can be of critical importance. So far, most conformal bounding box regression approaches do not simultaneously account for heteroscedasticity and dependencies between the residuals of each dimension. In this paper, we examine the importance of such dependencies and heteroscedasticity in the context of multi-target conformal regression, we apply copula-based conformal prediction methods to model them and to improve the volume of bounding box prediction regions. We compare these methods to the state-of-the-art conformal object detection approaches (on the KITTI & the BDD100K autonomous driving benchmarks) and the empirical copula-based method shows high-efficiency results that are robust w.r.t. heteroscedasticity and also robust w.r.t. the structure of the dependencies.
APA
Mukama, B.C., Messoudi, S., Rousseau, S. & Destercke, S.. (2024). Copula-based conformal prediction for object detection: a more efficient approach. Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 230:140-157 Available from https://proceedings.mlr.press/v230/mukama24a.html.

Related Material