English
Related papers

Related papers: Geometry-Aware Network for Domain Adaptive Semanti…

200 papers

Pre-trained 3D vision models have gained significant attention for their promising performance on point cloud data. However, fully fine-tuning these models for downstream tasks is computationally expensive and storage-intensive. Existing…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Zixiang Ai , Zichen Liu , Yuanhang Lei , Zhenyu Cui , Xu Zou , Jiahuan Zhou

Semantic segmentation suffers from significant performance degradation when the trained network is applied to a different domain. To address this issue, unsupervised domain adaptation (UDA) has been extensively studied. Despite the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Wangkai Li , Rui Sun , Huayu Mai , Tianzhu Zhang

Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases. In practice, the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Thanh-Dat Truong , Pierce Helton , Ahmed Moustafa , Jackson David Cothren , Khoa Luu

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Machine Learning · Computer Science 2025-04-02 Hoang Phan , Lam Tran , Quyen Tran , Trung Le

Unsupervised domain adaptation (UDA) is an approach to minimizing domain gap. Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e.g., cross-domain…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Yang Zhao , Peng Guo , Han Gao , Xiuwan Chen

Semantic segmentation on point clouds is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only features insufficient to distinguish objects with…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Hojun Song , Chae-yeong Song , Jeong-hun Hong , Chaewon Moon , Dong-hwi Kim , Gahyeon Kim , Soo Ye Kim , Yiyi Liao , Jaehyup Lee , Sang-hyo Park

Image-to-point cloud registration methods typically follow a coarse-to-fine pipeline, extracting patch-level correspondences and refining them into dense pixel-to-point matches. However, in scenes with repetitive patterns, images often lack…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zhixin Cheng , Jiacheng Deng , Xinjun Li , Bohao Liao , Li Liu , Xiaotian Yin , Baoqun Yin , Tianzhu Zhang

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics…

Cosmology and Nongalactic Astrophysics · Physics 2024-04-16 Andrea Roncoli , Aleksandra Ćiprijanović , Maggie Voetberg , Francisco Villaescusa-Navarro , Brian Nord

Deep learning frameworks allowed for a remarkable advancement in semantic segmentation, but the data hungry nature of convolutional networks has rapidly raised the demand for adaptation techniques able to transfer learned knowledge from…

Computer Vision and Pattern Recognition · Computer Science 2020-11-26 Marco Toldo , Umberto Michieli , Pietro Zanuttigh

Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…

Computer Vision and Pattern Recognition · Computer Science 2020-08-13 Sujoy Paul , Yi-Hsuan Tsai , Samuel Schulter , Amit K. Roy-Chowdhury , Manmohan Chandraker

We present a boundary-aware domain adaptation model for LiDAR scan full-scene semantic segmentation (LiDARNet). Our model can extract both the domain private features and the domain shared features with a two-branch structure. We embedded…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Peng Jiang , Srikanth Saripalli

Modern 3D-GANs synthesize geometry and texture by training on large-scale datasets with a consistent structure. Training such models on stylized, artistic data, with often unknown, highly variable geometry, and camera information has not…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Rameen Abdal , Hsin-Ying Lee , Peihao Zhu , Menglei Chai , Aliaksandr Siarohin , Peter Wonka , Sergey Tulyakov

Unsupervised domain adaptation (UDA) techniques are vital for semantic segmentation in geosciences, effectively utilizing remote sensing imagery across diverse domains. However, most existing UDA methods, which focus on domain alignment at…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Xianping Ma , Xiaokang Zhang , Xingchen Ding , Man-On Pun , Siwei Ma

Deep learning techniques have been widely used in autonomous driving systems for the semantic understanding of urban scenes. However, they need a huge amount of labeled data for training, which is difficult and expensive to acquire. A…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Umberto Michieli , Matteo Biasetton , Gianluca Agresti , Pietro Zanuttigh

Given the prominence of current 3D sensors, a fine-grained analysis on the basic point cloud data is worthy of further investigation. Particularly, real point cloud scenes can intuitively capture complex surroundings in the real world, but…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Shi Qiu , Saeed Anwar , Nick Barnes

In the face of the deep learning model's vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Uiwon Hwang , Jonghyun Lee , Juhyeon Shin , Sungroh Yoon

Data augmentation is widely used to train deep learning models to address data scarcity. However, traditional data augmentation (TDA) typically relies on simple geometric transformation, such as random rotation and rescaling, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Dekai Zhu , Stefan Gavranovic , Flavien Boussuge , Benjamin Busam , Slobodan Ilic

In this paper, we address the challenging source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation, given only a pinhole image pre-trained model (i.e., source) and unlabeled panoramic images (i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Xu Zheng , Pengyuan Zhou , Athanasios V. Vasilakos , Lin Wang

Unsupervised Domain Adaptation (UDA) for semantic segmentation has been favorably applied to real-world scenarios in which pixel-level labels are hard to be obtained. In most of the existing UDA methods, all target data are assumed to be…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Joonhyuk Kim , Sahng-Min Yoo , Gyeong-Moon Park , Jong-Hwan Kim

Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from…

Graphics · Computer Science 2022-01-14 Jiazhao Zhang , Chenyang Zhu , Lintao Zheng , Kai Xu