English
Related papers

Related papers: Compositional Semantic Mix for Domain Adaptation i…

200 papers

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framework based on…

Computer Vision and Pattern Recognition · Computer Science 2021-06-21 Jianzhong He , Xu Jia , Shuaijun Chen , Jianzhuang Liu

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Tianfang Sun , Zhizhong Zhang , Xin Tan , Yanyun Qu , Yuan Xie , Lizhuang Ma

Recently, semantic parsing has attracted much attention in the community. Although many neural modeling efforts have greatly improved the performance, it still suffers from the data scarcity issue. In this paper, we propose a novel semantic…

Computation and Language · Computer Science 2020-06-24 Zechang Li , Yuxuan Lai , Yansong Feng , Dongyan Zhao

The robust interpretation of 3D environments is crucial for human-robot collaboration (HRC) applications, where safety and operational efficiency are paramount. Semantic segmentation plays a key role in this context by enabling a precise…

Robotics · Computer Science 2025-06-12 Fatemeh Mohammadi Amin , Darwin G. Caldwell , Hans Wernher van de Venn

Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training…

Computer Vision and Pattern Recognition · Computer Science 2020-12-14 Ying Chen , Xu Ouyang , Kaiyue Zhu , Gady Agam

In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled data set from source domain and a target domain with a few labeled and many…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Eduardo R. Corral-Soto , Mrigank Rochan , Yannis Y. He , Shubhra Aich , Yang Liu , Liu Bingbing

As one of the fundamental tasks in computer vision, semantic segmentation plays an important role in real world applications. Although numerous deep learning models have made notable progress on several mainstream datasets with the rapid…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Bin Zhang , Shengjie Zhao , Rongqing Zhang

Domain adaptive point cloud completion (DA PCC) aims to narrow the geometric and semantic discrepancies between the labeled source and unlabeled target domains. Existing methods either suffer from limited receptive fields or quadratic…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Yinghui Li , Qianyu Zhou , Di Shao , Hao Yang , Ye Zhu , Richard Dazeley , Xuequan Lu

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Andrew Caunes , Thierry Chateau , Vincent Frémont

In this work, we present a simple yet effective framework to address the domain translation problem between different sensor modalities with unique data formats. By relying only on the semantics of the scene, our modular generative…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Tiago Cortinhal , Fatih Kurnaz , Eren Aksoy

Simulation-to-real domain adaptation for semantic segmentation has been actively studied for various applications such as autonomous driving. Existing methods mainly focus on a single-source setting, which cannot easily handle a more…

Computer Vision and Pattern Recognition · Computer Science 2019-10-29 Sicheng Zhao , Bo Li , Xiangyu Yue , Yang Gu , Pengfei Xu , Runbo Hu , Hua Chai , Kurt Keutzer

Deep learning approaches achieve prominent success in 3D semantic segmentation. However, collecting densely annotated real-world 3D datasets is extremely time-consuming and expensive. Training models on synthetic data and generalizing on…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Runyu Ding , Jihan Yang , Li Jiang , Xiaojuan Qi

Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the source and target…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Daehan Kim , Minseok Seo , Kwanyong Park , Inkyu Shin , Sanghyun Woo , In-So Kweon , Dong-Geol Choi

In unsupervised domain adaptation (UDA), directly adapting from the source to the target domain usually suffers significant discrepancies and leads to insufficient alignment. Thus, many UDA works attempt to vanish the domain gap gradually…

Computer Vision and Pattern Recognition · Computer Science 2022-10-12 Lin Chen , Zhixiang Wei , Xin Jin , Huaian Chen , Miao Zheng , Kai Chen , Yi Jin

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Shuaijun Chen , Xu Jia , Jianzhong He , Yongjie Shi , Jianzhuang Liu

In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation. The success of few-shot semantic segmentation in 2D computer vision is mainly driven by the pre-training on large-scale datasets…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Shuting He , Xudong Jiang , Wei Jiang , Henghui Ding

LiDAR point cloud semantic segmentation is essential for interpreting 3D environments in applications such as autonomous driving and robotics. Recent methods achieve strong performance by exploiting different point cloud representations or…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Simone Mosco , Daniel Fusaro , Wanmeng Li , Emanuele Menegatti , Alberto Pretto

Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data (source domain) adapt to real images (target domain). Previous feature-level adversarial learning methods only consider adapting models…

Computer Vision and Pattern Recognition · Computer Science 2021-09-21 Hongruixuan Chen , Chen Wu , Yonghao Xu , Bo Du

Annotating real-world LiDAR point clouds for use in intelligent autonomous systems is costly. To overcome this limitation, self-training-based Unsupervised Domain Adaptation (UDA) has been widely used to improve point cloud semantic…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Wanmeng Li , Simone Mosco , Daniel Fusaro , Alberto Pretto

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models trained on one data domain may not generalize well to other…

Computer Vision and Pattern Recognition · Computer Science 2019-09-30 Yi-Hsuan Tsai , Kihyuk Sohn , Samuel Schulter , Manmohan Chandraker