English
Related papers

Related papers: Unsupervised Domain Adaptation for Self-Driving fr…

200 papers

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Qiuhao Zeng , Wei Wang , Fan Zhou , Charles Ling , Boyu Wang

We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend existing unsupervised domain adaptive classification theories to…

Computer Vision and Pattern Recognition · Computer Science 2018-07-31 Liangchen Song , Cheng Wang , Lefei Zhang , Bo Du , Qian Zhang , Chang Huang , Xinggang Wang

In autonomous driving, 3D object detection is essential for accurately identifying and tracking objects. Despite the continuous development of various technologies for this task, a significant drawback is observed in most of them-they…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Hsin-Cheng Lu , Chung-Yi Lin , Winston H. Hsu

Detection of rare objects (e.g., traffic cones, traffic barrels and traffic warning triangles) is an important perception task to improve the safety of autonomous driving. Training of such models typically requires a large number of…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Naifan Li , Fan Song , Ying Zhang , Pengpeng Liang , Erkang Cheng

Autonomous vehicles often perceive the environment by feeding sensor data to a learned detector algorithm, then feeding detections to a multi-object tracker that models object motions over time. Probabilistic models of multi-object trackers…

Robotics · Computer Science 2019-09-19 Michael Motro , Joydeep Ghosh

3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic differences can…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Yecheol Kim , Junho Lee , Changsoo Park , Hyoung won Kim , Inho Lim , Christopher Chang , Jun Won Choi

3D semantic segmentation plays a pivotal role in autonomous driving and road infrastructure analysis, yet state-of-the-art 3D models are prone to severe domain shift when deployed across different datasets. In this paper, we propose an…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Andrew Caunes , Thierry Chateau , Vincent Fremont

Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperform on images from unseen geographies. We investigate the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Viraj Prabhu , Ramprasaath R. Selvaraju , Judy Hoffman , Nikhil Naik

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Petru Soviany , Radu Tudor Ionescu , Paolo Rota , Nicu Sebe

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success…

Computer Vision and Pattern Recognition · Computer Science 2022-08-17 Xiaofeng Liu , Chaehwa Yoo , Fangxu Xing , Hyejin Oh , Georges El Fakhri , Je-Won Kang , Jonghye Woo

In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Mrigank Rochan , Shubhra Aich , Eduardo R. Corral-Soto , Amir Nabatchian , Bingbing Liu

Current LiDAR-based 3D object detectors for autonomous driving are almost entirely trained on human-annotated data collected in specific geographical domains with specific sensor setups, making it difficult to adapt to a different domain.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-05 Jenny Xu , Steven L. Waslander

Unsupervised domain adaptation (UDA) plays a crucial role in object detection when adapting a source-trained detector to a target domain without annotated data. In this paper, we propose a novel and effective four-step UDA approach that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-30 Mohamed L. Mekhalfi , Davide Boscaini , Fabio Poiesi

Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Meiying Zhang , Weiyuan Peng , Guangyao Ding , Chenyang Lei , Chunlin Ji , Qi Hao

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Bo Zhang , Tao Chen , Bin Wang , Ruoyao Li

Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to…

Computer Vision and Pattern Recognition · Computer Science 2018-03-21 Jianming Lv , Weihang Chen , Qing Li , Can Yang

This paper addresses the problem of unsupervised domain adaptation on the task of pedestrian detection in crowded scenes. First, we utilize an iterative algorithm to iteratively select and auto-annotate positive pedestrian samples with high…

Computer Vision and Pattern Recognition · Computer Science 2018-02-12 Lihang Liu , Weiyao Lin , Lisheng Wu , Yong Yu , Michael Ying Yang

Accurate 3D object detection in LiDAR point clouds is crucial for autonomous driving systems. To achieve state-of-the-art performance, the supervised training of detectors requires large amounts of human-annotated data, which is expensive…

Computer Vision and Pattern Recognition · Computer Science 2024-08-08 Christian Fruhwirth-Reisinger , Wei Lin , Dušan Malić , Horst Bischof , Horst Possegger

Person re-identification is an open and challenging problem in computer vision. Existing approaches have concentrated on either designing the best feature representation or learning optimal matching metrics in a static setting where the…

Computer Vision and Pattern Recognition · Computer Science 2017-06-13 Rameswar Panda , Amran Bhuiyan , Vittorio Murino , Amit K. Roy-Chowdhury

LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Joshua Knights , Stephen Hausler , Sridha Sridharan , Clinton Fookes , Peyman Moghadam
‹ Prev 1 3 4 5 6 7 10 Next ›