Related papers: Revisiting Vicinal Risk Minimization for Partially…

Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to…

Accurate brain tumor segmentation from MRI is limited by expensive annotations and data heterogeneity across scanners and sites. We propose a semi-supervised teacher-student framework that combines an uncertainty-aware pseudo-labeling…

Medical image segmentation is a fundamental and critical step in many image-guided clinical approaches. Recent success of deep learning-based segmentation methods usually relies on a large amount of labeled data, which is particularly…

This work presents a novel deep learning framework for segmenting cerebral vasculature in hyperspectral brain images. We address the critical challenge of severe label scarcity, which impedes conventional supervised training. Our approach…

Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets. However, the availability of fully annotated atlas images for training is limited due…

In Multiple Instance learning (MIL), weak labels are provided at the bag level with only presence/absence information known. However, there is a considerable gap in performance in comparison to a fully supervised model, limiting the…

Recently, machine learning-based semantic segmentation algorithms have demonstrated their potential to accurately segment regions and contours in medical images, allowing the precise location of anatomical structures and abnormalities.…

Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely…

Neural network approaches have recently shown to be effective in several information retrieval (IR) tasks. However, neural approaches often require large volumes of training data to perform effectively, which is not always available. To…

Semi-supervised medical image segmentation has gained growing interest due to its ability to utilize unannotated data. The current state-of-the-art methods mostly rely on pseudo-labeling within a co-training framework. These methods depend…

Many classification problems involve data instances that are interlinked with each other, such as webpages connected by hyperlinks. Techniques for "collective classification" (CC) often increase accuracy for such data graphs, but usually…

This paper presents privileged multi-label learning (PrML) to explore and exploit the relationship between labels in multi-label learning problems. We suggest that for each individual label, it cannot only be implicitly connected with other…

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community. In this paper,…

Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy…

Existing weak supervision approaches use all the data covered by weak signals to train a classifier. We show both theoretically and empirically that this is not always optimal. Intuitively, there is a tradeoff between the amount of…

The semi-supervised semantic segmentation (S4) can learn rich visual knowledge from low-cost unlabeled images. However, traditional S4 architectures all face the challenge of low-quality pseudo-labels, especially for the teacher-student…

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…

Various strategies for label-scarce object detection have been explored by the computer vision research community. These strategies mainly rely on assumptions that are specific to natural images and not directly applicable to the biological…

Multi-instrument recognition is the task of predicting the presence or absence of different instruments within an audio clip. A considerable challenge in applying deep learning to multi-instrument recognition is the scarcity of labeled…

The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy…