Search Results

Removing undesired shading from human images is crucial in supporting various real-world applications. While recent advancements in deep learning-based methods show promise in addressing this challenge, there persists a struggle to accurately ...

In a multi-label learning problem, each instance is associated with multiple labels simultaneously. However, problem becomes more complicated when labels are missing. Many multi-label based real-life applications, such as medical diagnosis, ...

For traffic incident detection, the acquisition of data and labels is notably resource-intensive, rendering semi-supervised traffic incident detection both a formidable and consequential challenge. Thus, this paper focuses on traffic incident ...

In the prevention and treatment of hemorrhagic stroke, it is of great significance to judge and select influencing factors as well as make treatment plans through modern intelligent medical methods based on machine learning algorithm. In this paper, we ...

Conversion rate (CVR) prediction is essential in recommender systems, facilitating precise matching between recommended items and users’ preferences. However, the sample selection bias (SSB) and data sparsity (DS) issues pose challenges to accurate ...

Semi-supervised learning (SSL) has attracted much attention since it reduces the expensive costs of collecting adequate well-labeled training data, especially for deep learning methods. However, traditional SSL is built upon an assumption that ...

When developing Computer Aided Detection (CAD) systems for Digital Breast Tomosynthesis (DBT), the complexity arising from the volumetric nature of the modality poses significant technical challenges for obtaining large-scale accurate annotations. ...

In computational pathology, deep learning (DL) models for tasks such as segmentation or tissue classification are known to suffer from domain shifts due to different staining techniques. Stain adaptation aims to reduce the generalization error ...

Diagnosis of lymph node (LN) metastasis in computed tomography (CT) scans is an essential yet challenging task for esophageal cancer staging and treatment planning. Deep learning methods can potentially address this issue by learning from large-...$\mathrm{}$$\mathrm{}$$\mathrm{}$

In semi-supervised medical image segmentation (SSMIS), existing methods typically impose consistency or contrastive regularizations under basic data and network perturbations, and individually segment each voxel/pixel in the image. In fact, a ...

Semi-supervised learning (SSL) has shown its effectiveness in learning effective 3D representation from a small amount of labelled data while utilizing large unlabelled data. Traditional semi-supervised approaches rely on the fundamental concept ...

Semi-supervised learning is a learning method that uses both labeled and unlabeled samples to improve the performance of the model while reducing labeling costs. When there were tens to hundreds of labeled samples, semi-supervised learning methods ...

Generalized Category Discovery (GCD) utilizes labelled data from seen categories to cluster unlabelled samples from both seen and unseen categories. Previous methods have demonstrated that assigning pseudo-labels for representation learning is ...

The pseudo-labelling algorithm is highly effective across various tasks, particularly in semi-supervised learning, yet its vulnerabilities are not always apparent on benchmark datasets, leading to suboptimal real-world performance. In this paper, ...

Existing action quality assessment (AQA) methods often require a large number of label annotations for fully supervised learning, which are laborious and expensive. In practice, the labeled data are difficult to obtain because the AQA annotation ...

Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. This problem is often aggravated by discrepancies between labeled and ...

Semi-supervised medical image segmentation has shown promise in training models with limited labeled data. However, current dominant teacher-student based approaches can suffer from the confirmation bias. To address this challenge, we propose AD-...

The costly and time-consuming annotation process to produce large training sets for modelling semantic LiDAR segmentation methods has motivated the development of semi-supervised learning (SSL) methods. However, such SSL approaches often ...

Medical image segmentation plays a vital role in healthcare, serving as an indispensable tool for delineating anatomical structures essential for diagnostic accuracy and treatment planning. And it is also an interesting computer vision challenge. ...

Document dewarping has made great progress in recent years, however it usually requires huge document pairs with pixel-level annotation to learn a mapping function. Although photographed document images are easy to obtain, the pixel-level ...$$