홈 › Papers

WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection

2024-07-30 · Xingcheng Zhou, Deyu Fu, Walter Zimmer, MingYu Liu, Venkatnarayanan Lakshminarasimhan, Leah Strand, Alois C. Knoll

Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this challenge and enhance the performance of roadside monocular 3D detection. In this study, we introduce the TUMTraf Synthetic Dataset, offering a diverse and substantial collection of high-quality 3D data to augment scarce real-world datasets. Besides, we present WARM-3D, a concise yet effective framework to aid the Sim2Real domain transfer for roadside monocular 3D detection. Our method leverages cheap synthetic datasets and 2D labels from an off-the-shelf 2D detector for weak supervision. We show that WARM-3D significantly enhances performance, achieving a +12.40% increase in mAP 3D over the baseline with only pseudo-2D supervision. With 2D GT as weak labels, WARM-3D even reaches performance close to the Oracle baseline. Moreover, WARM-3D improves the ability of 3D detectors to unseen sample recognition across various real-world environments, highlighting its potential for practical applications.

📄 PDF Abstract BibTeX arXiv:2407.20818

Code (1)

WARM-3D/WARM-3D pytorch

Tasks

3D Object Detection Domain Adaptation Monocular 3D Object Detection object-detection Object Detection

D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation

2022-12-02 · Yuting Wang, Ricardo Guerrero, Vladimir Pavlovic

Weakly-supervised object detection (WSOD) models attempt to leverage image-level annotations in lieu of accurate but costly-to-obtain object localization labels. This oftentimes leads to substandard object detection and …

Domain Adaptation Object object-detection Object Detection+2

ACTIVE REFINEMENT OF WEAKLY SUPERVISED MODELS

2021-09-29 · Mononito Goswami, Chufan Gao, Benedikt Boecking, Saswati Ray 외

Supervised machine learning (ML) has fueled major advances in several domains such as health, education and governance. However, most modern ML methods rely on vast quantities of point-by-point hand-labeled training data…

Active Learning

1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track

2023-01-12 · Wei Zhao, Binbin Chen, WeiJie Chen, Shicai Yang 외

OOD-CV challenge is an out-of-distribution generalization task. To solve this problem in object detection track, we propose a simple yet effective Generalize-then-Adapt (G&A) framework, which is composed of a two-stage d…

Domain Adaptation Domain Generalization object-detection Object Detection+2

WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection

2023-10-05 · Tsung-Lin Tsou, Tsung-Han Wu, Winston H. Hsu

In the field of domain adaptation (DA) on 3D object detection, most of the work is dedicated to unsupervised domain adaptation (UDA). Yet, without any target annotations, the performance gap between the UDA approaches an…

3D Object Detection Domain Adaptation object-detection Object Detection+1

Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration

2019-04-30 · CVPR 2019 6 · Shuhan Tan, Jiening Jiao, Wei-Shi Zheng

In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the r…

Domain Adaptation Transfer Learning