English
Related papers

Related papers: XD-MAP: Cross-Modal Domain Adaptation via Semantic…

200 papers

Recently, large-scale pre-trained models such as Segment-Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP) have demonstrated remarkable success and revolutionized the field of computer vision. These foundation vision…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Shichao Dong , Fayao Liu , Guosheng Lin

Point cloud maps generated via LiDAR sensors using extensive remotely sensed data are commonly used by autonomous vehicles and robots for localization and navigation. However, dynamic objects contained in point cloud maps not only downgrade…

Robotics · Computer Science 2024-02-29 Feiya Li , Chunyun Fu , Dongye Sun , Jian Li , Jianwen Wang

Semantic segmentation networks trained under full supervision for one type of lidar fail to generalize to unseen lidars without intervention. To reduce the performance gap under domain shifts, a recent trend is to leverage vision foundation…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Björn Michele , Alexandre Boulch , Gilles Puy , Tuan-Hung Vu , Renaud Marlet , Nicolas Courty

The majority of learning-based semantic segmentation methods are optimized for daytime scenarios and favorable lighting conditions. Real-world driving scenarios, however, entail adverse environmental conditions such as nighttime…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 Johan Vertens , Jannik Zürn , Wolfram Burgard

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Junwen Huang , Alexey Artemov , Yujin Chen , Shuaifeng Zhi , Kai Xu , Matthias Nießner

One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations,…

Computer Vision and Pattern Recognition · Computer Science 2021-09-29 Rui Gong , Dengxin Dai , Yuhua Chen , Wen Li , Luc Van Gool

Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Peng Tu , Yawen Huang , Rongrong Ji , Feng Zheng , Ling Shao

Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data…

Computer Vision and Pattern Recognition · Computer Science 2019-02-14 Fabio Maria Carlucci

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Juncheng Yang , Zuchao Li , Shuai Xie , Weiping Zhu , Wei Yu , Shijun Li

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 Francesco Barbato , Umberto Michieli , Marco Toldo , Pietro Zanuttigh

Flexible sensors hold promise for human motion capture (MoCap), offering advantages such as wearability, privacy preservation, and minimal constraints on natural movement. However, existing flexible sensor-based MoCap methods rely on deep…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Jiawei Fang , Haishan Song , Chengxu Zuo , Xiaoxia Gao , Xiaowei Chen , Shihui Guo , Yipeng Qin

Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different…

Computer Vision and Pattern Recognition · Computer Science 2019-10-25 Han-Kai Hsu , Chun-Han Yao , Yi-Hsuan Tsai , Wei-Chih Hung , Hung-Yu Tseng , Maneesh Singh , Ming-Hsuan Yang

A deep learning model trained on some labeled data from a certain source domain generally performs poorly on data from different target domains due to domain shifts. Unsupervised domain adaptation methods address this problem by alleviating…

Image and Video Processing · Electrical Eng. & Systems 2019-08-30 Junlin Yang , Nicha C. Dvornek , Fan Zhang , Julius Chapiro , MingDe Lin , James S. Duncan

Despite the increasing popularity of LiDAR sensors, perception algorithms using 3D LiDAR data struggle with the 'sensor-bias problem'. Specifically, the performance of perception algorithms significantly drops when an unseen specification…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Kwonyoung Ryu , Soonmin Hwang , Jaesik Park

Deep learning applications on LiDAR data suffer from a strong domain gap when applied to different sensors or tasks. In order for these methods to obtain similar accuracy on different data in comparison to values reported on public…

Computer Vision and Pattern Recognition · Computer Science 2023-09-13 Laurenz Reichardt , Nikolas Ebert , Oliver Wasenmüller

Recent deep learning-based methods outperform traditional learning methods on remote sensing (RS) semantic segmentation/classification tasks. However, they require large training datasets and are generally known for lack of transferability…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Rongjun Qin , Guixiang Zhang , Yang Tang

Style transfer generates an image whose content comes from one image and style from the other. Image-to-image translation approaches with disentangled representations have been shown effective for style transfer between two image…

Computer Vision and Pattern Recognition · Computer Science 2020-08-06 Hsin-Yu Chang , Zhixiang Wang , Yung-Yu Chuang

Using deep learning, 3D autonomous driving semantic segmentation has become a well-studied subject, with methods that can reach very high performance. Nonetheless, because of the limited size of the training datasets, these models cannot…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Jules Sanchez , Jean-Emmanuel Deschaud , Francois Goulette

The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors. Notably, radar sensors show greater robustness compared to cameras and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Miao Zhang , Sherif Abdulatif , Benedikt Loesch , Marco Altmann , Marius Schwarz , Bin Yang

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…

Computer Vision and Pattern Recognition · Computer Science 2020-07-02 Haiyang Liu , Yichen Wang , Jiayi Zhao , Guowu Yang , Fengmao Lv