Go to ICLR 2025 Conference homepageUncertainty Estimation for 3D Object Detection via Evidential Learning
Keywords: 3d;detection;uncertainty
TL;DR: a method that leverages model uncertainty to improve performance in the 3D object detection task
Abstract: 3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics.
However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes.
We introduce a framework for quantifying uncertainty in 3D object detection by leveraging an evidential learning loss on Bird's Eye View representations in the 3D detector.
These uncertainty estimates require minimal computational overhead and are generalizable across different architectures.
We demonstrate both the efficacy and importance of these uncertainty estimates on identifying out-of-distribution scenes, poorly localized objects, and missing (false negative) detections; our framework consistently improves over baselines by 10-20\% on average.
Finally, we integrate this suite of tasks into a system where a 3D object detector auto-labels driving scenes and our uncertainty estimates verify label correctness before the labels are used to train a second model. Here, our uncertainty-driven verification results in a 1\% improvement in mAP and a 1-2\% improvement in NDS.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 4014
Loading