MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909540890443776 |
|---|---|
| author | Meier, Johannes Inchingolo, Louis Dhaouadi, Oussema Xia, Yan Kaiser, Jacques Cremers, Daniel |
| author_facet | Meier, Johannes Inchingolo, Louis Dhaouadi, Oussema Xia, Yan Kaiser, Jacques Cremers, Daniel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13743 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models Meier, Johannes Inchingolo, Louis Dhaouadi, Oussema Xia, Yan Kaiser, Jacques Cremers, Daniel Computer Vision and Pattern Recognition 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. |
| title | MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.13743 |