English
Related papers

Related papers: LoopDA: Constructing Self-loops to Adapt Nighttime…

200 papers

Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Lucas Nunes , Rodrigo Marcuzzi , Jens Behley , Cyrill Stachniss

Solving the domain shift problem during inference is essential in medical imaging, as most deep-learning based solutions suffer from it. In practice, domain shifts are tackled by performing Unsupervised Domain Adaptation (UDA), where a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Vibashan VS , Jeya Maria Jose Valanarasu , Vishal M. Patel

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Silvia Bucci , Antonio D'Innocente , Yujun Liao , Fabio Maria Carlucci , Barbara Caputo , Tatiana Tommasi

Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Yeonguk Yu , Sungho Shin , Seunghyeok Back , Minhwan Ko , Sangjun Noh , Kyoobin Lee

Autonomous vehicles clearly benefit from the expanded Field of View (FoV) of 360-degree sensors, but modern semantic segmentation approaches rely heavily on annotated training data which is rarely available for panoramic images. We look at…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Jiaming Zhang , Chaoxiang Ma , Kailun Yang , Alina Roitberg , Kunyu Peng , Rainer Stiefelhagen

3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Bartłomiej Olber , Jakub Winter , Paweł Wawrzyński , Andrii Gamalii , Daniel Górniak , Marcin Łojek , Robert Nowak , Krystian Radlak

In this paper, we tackle the unsupervised domain adaptation (UDA) for semantic segmentation, which aims to segment the unlabeled real data using labeled synthetic data. The main problem of UDA for semantic segmentation relies on reducing…

Computer Vision and Pattern Recognition · Computer Science 2020-12-24 Suhyeon Lee , Junhyuk Hyun , Hongje Seong , Euntai Kim

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Javed Iqbal , Hamza Rawal , Rehan Hafiz , Yu-Tseh Chi , Mohsen Ali

Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…

Machine Learning · Computer Science 2020-11-25 Qun Liu , Matthew Shreve , Raja Bala

Monocular depth estimation (MDE) has attracted intense study due to its low cost and critical functions for robotic tasks such as localization, mapping and obstacle detection. Supervised approaches have led to great success with the advance…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Shao-Yuan Lo , Wei Wang , Jim Thomas , Jingjing Zheng , Vishal M. Patel , Cheng-Hao Kuo

Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them suffer from noticeable performance degradation due to the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-16 Dingding Cai , Janne Heikkilä , Esa Rahtu

Instance segmentation is crucial for autonomous driving, but is hindered by the lack of annotated real-world data due to expensive labeling costs. Unsupervised Domain Adaptation (UDA) offers a solution by transferring knowledge from labeled…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Yachan Guo , Yi Xiao , Danna Xue , Jose L. Gomez , Antonio M. Lopez

In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle's surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Junbao Zhou , Jilin Mei , Pengze Wu , Liang Chen , Fangzhou Zhao , Xijun Zhao , Yu Hu

The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for RGB-Thermal (RGB-T) semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Yexin Liu , Weiming Zhang , Guoyang Zhao , Jinjing Zhu , Athanasios Vasilakos , Lin Wang

Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Da Li , Timothy Hospedales

Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically do not generalize well when applied on new domains,…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Wilhelm Tranheden , Viktor Olsson , Juliano Pinto , Lennart Svensson

Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real…

Computer Vision and Pattern Recognition · Computer Science 2019-08-13 Yuhu Shan , Wen Feng Lu , Chee Meng Chew

Semantic segmentation of 3D geospatial point clouds is fundamental to remote sensing applications, yet domain shifts caused by regional and acquisition-related variations often degrade model performance. Although domain adaptation can…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Yuan Gao , Di Cao , Xiaohuan Xi , Sheng Nie , Shaobo Xia , Cheng Wang

Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation. However, training a neural network in a supervised manner requires a large amount of annotated labels which…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Dongseok Shim , H. Jin Kim

Universal domain adaptation (UniDA) transfers knowledge from a labeled source domain to an unlabeled target domain, where label spaces may differ and the target domain may contain private classes. Previous UniDA methods primarily focused on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Dujin Lee , Sojung An , Jungmyung Wi , Kuniaki Saito , Donghyun Kim