English
Related papers

Related papers: Spatial regularisation for improved accuracy and i…

200 papers

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 presents a simple yet effective two-stage framework for semi-supervised medical image segmentation. Unlike prior state-of-the-art semi-supervised segmentation methods that predominantly rely on pseudo supervision directly on…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Huimin Wu , Xiaomeng Li , Kwang-Ting Cheng

Many loss functions have been derived from cross-entropy loss functions such as large-margin softmax loss and focal loss. The large-margin softmax loss makes the classification more rigorous and prevents overfitting. The focal loss…

Computer Vision and Pattern Recognition · Computer Science 2023-02-10 Jiajie Chen

Semi-supervised learning (SSL) has been proven to be a powerful method for leveraging unlabeled data to alleviate models'dependence on large labeled datasets. The common framework among recent approaches is to train the model on a large…

Machine Learning · Computer Science 2026-03-19 Jun Sun , Wancheng Zhang , Chao Zhou , Zhongjie Mao , Chao Li , Xiao-Jun Wu

A reliable Ultrasound (US)-to-US registration method to compensate for brain shift would substantially improve Image-Guided Neurological Surgery. Developing such a registration method is very challenging, due to factors such as missing…

Weakly-supervised learning (WSL) has recently triggered substantial interest as it mitigates the lack of pixel-wise annotations. Given global image labels, WSL methods yield pixel-level predictions (segmentations), which enable to interpret…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Soufiane Belharbi , Jérôme Rony , Jose Dolz , Ismail Ben Ayed , Luke McCaffrey , Eric Granger

Sparse hyperspectral unmixing from large spectral libraries has been considered to circumvent limitations of endmember extraction algorithms in many applications. This strategy often leads to ill-posed inverse problems, which can benefit…

Computer Vision and Pattern Recognition · Computer Science 2018-10-29 Ricardo Augusto Borsoi , Tales Imbiriba , José Carlos Moreira Bermudez , Cédric Richard

Recently, self-supervised learning (SSL) methods have been used in pre-training the segmentation models for 2D and 3D medical images. Most of these methods are based on reconstruction, contrastive learning and consistency regularization.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Haofeng Li , Yiming Ouyang , Xiang Wan

We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robust 3D semantic Gaussian Splatting. The 2D features extracted…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Zaiyan Yang , Xinpeng Liu , Heng Guo , Jinglei Shi , Zhanyu Ma , Fumio Okura

We introduce a method for fast estimation of data-adapted, spatio-temporally dependent regularization parameter-maps for variational image reconstruction, focusing on total variation (TV)-minimization. Our approach is inspired by recent…

During the inversion of discrete linear systems noise in data can be amplified and result in meaningless solutions. To combat this effect, characteristics of solutions that are considered desirable are mathematically implemented during…

Numerical Analysis · Mathematics 2023-02-07 Michael J. Byrne , Rosemary A. Renaut

We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint…

Machine Learning · Statistics 2015-04-02 Junhong Lin , Lorenzo Rosasco , Ding-Xuan Zhou

Pretraining CNN models (i.e., UNet) through self-supervision has become a powerful approach to facilitate medical image segmentation under low annotation regimes. Recent contrastive learning methods encourage similar global representations…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Zhangsihao Yang , Mengwei Ren , Kaize Ding , Guido Gerig , Yalin Wang

There exist many high-dimensional data in real-world applications such as biology, computer vision, and social networks. Feature selection approaches are devised to confront with high-dimensional data challenges with the aim of efficient…

Machine Learning · Computer Science 2021-06-22 Mohsen Ghassemi Parsa , Hadi Zare , Mehdi Ghatee

Over recent years, deep learning based image registration has achieved impressive accuracy in many domains, including medical imaging and, specifically, human neuroimaging with magnetic resonance imaging (MRI). However, the uncertainty…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Xiaoling Hu , Karthik Gopinath , Peirong Liu , Malte Hoffmann , Koen Van Leemput , Oula Puonti , Juan Eugenio Iglesias

Recent attempts for unsupervised landmark learning leverage synthesized image pairs that are similar in appearance but different in poses. These methods learn landmarks by encouraging the consistency between the original images and the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-03 Yinghao Xu , Ceyuan Yang , Ziwei Liu , Bo Dai , Bolei Zhou

Reliable quantification of uncertainty in Mobile Laser Scanning (MLS) point clouds is essential for ensuring the accuracy and credibility of downstream applications such as 3D mapping, modeling, and change analysis. Traditional backward…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Ziyang Xu , Olaf Wysocki , Christoph Holst

We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration. Contrary to optimization-based registration techniques and many modern learning-based methods, we do not…

Driving scene parsing is critical for autonomous vehicles to operate reliably in complex real-world traffic environments. To reduce the reliance on costly pixel-level annotations, synthetic datasets with automatically generated labels have…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Jiahe Fan , Xiao Ma , Sergey Vityazev , George Giakos , Shaolong Shu , Rui Fan

Most recent unsupervised non-rigid 3D shape matching methods are based on the functional map framework due to its efficiency and superior performance. Nevertheless, respective methods struggle to obtain spatially smooth pointwise…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Dongliang Cao , Zorah Laehner , Florian Bernard