English
Related papers

Related papers: Unsupervised Landmark Discovery Using Consistency …

200 papers

In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Zijia Lu , Bing Shuai , Yanbei Chen , Zhenlin Xu , Davide Modolo

Visual localization is a core technology for augmented reality and autonomous navigation. Recent methods combine the efficient rendering of 3D Gaussian Splatting (3DGS) with feature-based localization. These methods rely on direct matching…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Yingdong Gu , Shaocheng Yan , Zhenjun Zhao , Yuan Kou , Jianxin Luo , Pengcheng Shi , Jiayuan Li

Deep learning techniques have greatly enhanced the performance of fire detection in videos. However, video-based fire detection models heavily rely on labeled data, and the process of data labeling is particularly costly and time-consuming,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Qinghua Lin , Zuoyong Li , Kun Zeng , Haoyi Fan , Wei Li , Xiaoguang Zhou

Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Xiaohui Liu , Zhilu Zhang , Xiaohe Wu , Chaoyu Feng , Xiaotao Wang , Lei Lei , Wangmeng Zuo

This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes. While many prior studies have focused on improving image-matching performance…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Khang Truong Giang , Soohwan Song , Sungho Jo

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…

Machine Learning · Computer Science 2019-11-20 Qian Wang , Toby P. Breckon

Pseudo-label based self training approaches are a popular method for source-free unsupervised domain adaptation. However, their efficacy depends on the quality of the labels generated by the source trained model. These labels may be…

Computer Vision and Pattern Recognition · Computer Science 2021-10-01 Deepti Hegde , Vishwanath Sindagi , Velat Kilic , A. Brinton Cooper , Mark Foster , Vishal Patel

Unlabeled LiDAR logs, in autonomous driving applications, are inherently a gold mine of dense 3D geometry hiding in plain sight - yet they are almost useless without human labels, highlighting a dominant cost barrier for…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Filippo Ghilotti , Samuel Brucker , Nahku Saidy , Matteo Matteucci , Mario Bijelic , Felix Heide

Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation. However, this assumption is often infeasible owing to confidentiality issues or memory constraints on mobile devices.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 JoonHo Lee , Gyemin Lee

Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets.…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Mike Kasper , Fernando Nobre , Christoffer Heckman , Nima Keivan

The prevailing methodology in data-driven fault detection leverages synthetic data for training neural networks. However, it grapples with challenges when it comes to generalization in surveys exhibiting complex structures. To enhance the…

Geophysics · Physics 2024-10-28 Yimin Dou , Minghui Dong , Kewen Li , Y uan Xiao

Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance. Specifically, the semantic ambiguity means that some…

Computer Vision and Pattern Recognition · Computer Science 2019-03-27 Zhiwei Liu , Xiangyu Zhu , Guosheng Hu , Haiyun Guo , Ming Tang , Zhen Lei , Neil M. Robertson , Jinqiao Wang

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Rongchang Xie , Chunyu Wang , Wenjun Zeng , Yizhou Wang

Digital camera pipelines employ color constancy methods to estimate an unknown scene illuminant, in order to re-illuminate images as if they were acquired under an achromatic light source. Fully-supervised learning approaches exhibit…

Computer Vision and Pattern Recognition · Computer Science 2019-04-05 Steven McDonagh , Sarah Parisot , Fengwei Zhou , Xing Zhang , Ales Leonardis , Zhenguo Li , Gregory Slabaugh

Knowledge about the locations of keypoints of an object in an image can assist in fine-grained classification and identification tasks, particularly for the case of objects that exhibit large variations in poses that greatly influence their…

Computer Vision and Pattern Recognition · Computer Science 2021-01-21 Olga Moskvyak , Frederic Maire , Feras Dayoub , Mahsa Baktashmotlagh

Predicting attention regions of interest is an important yet challenging task for self-driving systems. Existing methodologies rely on large-scale labeled traffic datasets that are labor-intensive to obtain. Besides, the huge domain gap…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Pengfei Zhu , Mengshi Qi , Xia Li , Weijian Li , Huadong Ma

We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences. Existing unsupervised methods often exploit brightness constancy and…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Yuliang Zou , Zelun Luo , Jia-Bin Huang

We present two techniques to improve landmark localization in images from partially annotated datasets. Our primary goal is to leverage the common situation where precise landmark locations are only provided for a small data subset, but…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Sina Honari , Pavlo Molchanov , Stephen Tyree , Pascal Vincent , Christopher Pal , Jan Kautz

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground…

Computer Vision and Pattern Recognition · Computer Science 2020-10-16 Zhedong Zheng , Yi Yang

Medical image segmentation is a fundamental and critical step in many clinical approaches. Semi-supervised learning has been widely applied to medical image segmentation tasks since it alleviates the heavy burden of acquiring…

Image and Video Processing · Electrical Eng. & Systems 2022-08-29 Yichi Zhang , Rushi Jiao , Qingcheng Liao , Dongyang Li , Jicong Zhang