MEDL-U: Uncertainty-aware 3D Automatic Annotator Based on Evidential Deep Learning

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


MPhil Thesis Defence


Title: "MEDL-U: Uncertainty-aware 3D Automatic Annotator Based on Evidential
Deep Learning"

By

Mr. Helbert Agluba PAAT


Abstract:

Advancements in deep learning-based 3D object detection necessitate the
availability of large-scale datasets. However, this requirement introduces the
challenge of manual annotation, which is often both burdensome and
time-consuming. To tackle this issue, the literature has seen the emergence of
several weakly supervised frameworks for 3D object detection which can
automatically generate pseudo labels for unlabeled data. Nevertheless, these
generated pseudo labels contain noise and are not as accurate as those labeled
by humans. In this paper, we present the first approach that addresses the
inherent ambiguities present in pseudo labels by introducing an Evidential Deep
Learning (EDL) based uncertainty estimation framework. Specifically, we propose
MEDL-U, an EDL framework based on MTrans, which not only generates pseudo
labels but also quantifies the associated uncertainties. However, applying EDL
to 3D object detection presents three primary challenges: (1) relatively lower
pseudo label quality in comparison to other autolabelers; (2) excessively high
evidential uncertainty estimates; and (3) lack of clear interpretability and
effective utilization of uncertainties for downstream tasks. We tackle these
issues through the introduction of an uncertainty-aware IoU-based loss, an
evidence-aware multi-task loss, and the implementation of a post-processing
stage for uncertainty refinement. Our experimental results demonstrate that
probabilistic detectors trained using the outputs of MEDL-U surpass
deterministic detectors trained using outputs from previous 3D annotators on
the KITTI val set for all difficulty levels. Moreover, MEDL-U achieves
state-of-the-art results on the KITTI official test set compared to existing 3D
automatic annotators.


Date:                   Tuesday, 21 November 2023

Time:                   4:00pm - 6:00pm

Venue:                  Room CYTG002
                        lifts 35/36

Committee Members:      Prof. Tong Zhang (Supervisor)
                        Prof. Dit Yan Yeung (Chairperson)
                        Prof. Pedro Sander


**** ALL are Welcome ****