DODA: Data-Oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation

Ding, Runyu; Yang, Jihan; Jiang, Li; Qi, Xiaojuan

doi:10.1007/978-3-031-19812-0_17

Cited by 11 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[281,282] contributes with a systematic literature review in computer vision domain adaptation, identifying vital research topics [283]. These studies highlight the potential of domain adaptation across diverse domains, including object detection in video [284], face recognition [285], medical image analysis [286], natural language processing [287], robotics [288,289], 3D vision [290][291][292], etc. Additionally, specialized strategies like multi-task learning [293][294][295] and transfer learning [296] demonstrate their capability to achieve state-of-the-art performance across various visual recognition tasks and learn domain-invariant representations.…”

Section: Paper Contribution Advantagesmentioning

confidence: 99%

An In-Depth Analysis of Domain Adaptation in Computer and Robotic Vision

Tanveer,

Fatima,

Zardari

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

This review article comprehensively delves into the rapidly evolving field of domain adaptation in computer and robotic vision. It offers a detailed technical analysis of the opportunities and challenges associated with this topic. Domain adaptation methods play a pivotal role in facilitating seamless knowledge transfer and enhancing the generalization capabilities of computer and robotic vision systems. Our methodology involves systematic data collection and preparation, followed by the application of diverse assessment metrics to evaluate the efficacy of domain adaptation strategies. This study assesses the effectiveness and versatility of conventional, deep learning-based, and hybrid domain adaptation techniques within the domains of computer and robotic vision. Through a cross-domain analysis, we scrutinize the performance of these approaches in different contexts, shedding light on their strengths and limitations. The findings gleaned from our evaluation of specific domains and models offer valuable insights for practical applications while reinforcing the validity of the proposed methodologies.

show abstract

Section: Paper Contribution Advantagesmentioning

confidence: 99%

An In-Depth Analysis of Domain Adaptation in Computer and Robotic Vision

Tanveer,

Fatima,

Zardari

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Label/Data-Efficient Learning for 3D. Recent studies have produced many elaborately designed backbone networks for 3D semantic/instance segmentation [45], [88], [89], [90], [91], as well as for 3D object detection [92], [93], [94], [95]. However, they rely on full supervision.…”

Section: Related Workmentioning

confidence: 99%

RM3D: Robust Data-Efficient 3D Scene Parsing via Traditional and Learnt 3D Descriptors-Based Semantic Region Merging

Liu

2022

Int J Comput Vis

View full text Add to dashboard Cite

Existing state-of-the-art 3D point cloud understanding methods merely perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework that simultaneously solves the downstream high-level understanding tasks including both segmentation and detection, especially when labels are extremely limited. This work presents a general and simple framework to tackle point cloud understanding when labels are limited. The first contribution is that we have done extensive methodology comparisons of traditional and learned 3D descriptors for the task of weakly supervised 3D scene understanding, and validated that our adapted traditional PFH-based 3D descriptors show excellent generalization ability across different domains. The second contribution is that we proposed a learning-based region merging strategy based on the affinity provided by both the traditional/learned 3D descriptors and learned semantics. The merging process takes both low-level geometric and high-level semantic feature correlations into consideration. Experimental results demonstrate that our framework has the best performance among the three most important weakly supervised point clouds understanding tasks including semantic segmentation, instance segmentation, and object detection even when very limited number of points are labeled. Our method, termed Region Merging 3D (RM3D), has superior performance on Scan-Net data-efficient learning online benchmarks and other four large-scale 3D understanding benchmarks under various experimental settings, outperforming current arts by a margin for various 3D understanding tasks without complicated learning strategies such as active learning.

show abstract

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding

Jiang,

Zhou,

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

DODA: Data-Oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation

Cited by 11 publications

References 51 publications

An In-Depth Analysis of Domain Adaptation in Computer and Robotic Vision

An In-Depth Analysis of Domain Adaptation in Computer and Robotic Vision

RM3D: Robust Data-Efficient 3D Scene Parsing via Traditional and Learnt 3D Descriptors-Based Semantic Region Merging

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding

Contact Info

Product

Resources

About