MonoCT: Overcoming Monocular 3D Detection Domain Shift With Consistent Teacher Models
MCML Authors
Yan Xia
Dr.
* Former Member
Daniel Cremers
Prof. Dr.
Director
Abstract
Yan Xia
Dr.
* Former Member
Daniel Cremers
Prof. Dr.
Director
Abstract
We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly accurate pseudo labels for self-supervision. Inspired by our observation that accurate depth estimation is critical to mitigating domain shifts, MonoCT introduces a novel Generalized Depth Enhancement (GDE) module with an ensemble concept to improve depth estimation accuracy. Moreover, we introduce a novel Pseudo Label Scoring (PLS) module by exploring inner-model consistency measurement and a Diversity Maximization (DM) strategy to further generate high-quality pseudo labels for self-training. Extensive experiments on six benchmarks show that MonoCT outperforms existing SOTA domain adaptation methods by large margins (~21% minimum for AP Mod.) and generalizes well to car, traffic camera and drone views.
inproceedings
IV 2025
36th IEEE Intelligent Vehicles Symposium. Napoca, Romania, Jun 22-25, 2025. To be published. Preprint available.Authors
J. Meier • L. Inchingolo • O. Dhaouadi • Y. Xia • J. Kaiser • D. CremersLinks
Research Area
BibTeXKey: MID+25a