Deep learning empowers the mainstream medical image segmentation methods...
The paradigm of machine intelligence moves from purely supervised learni...
Exemplar-free Class-incremental Learning (CIL) is a challenging problem
...
Task-free continual learning (CL) aims to learn a non-stationary data st...
Object tracking is one of the fundamental problems in visual recognition...
The abundance of data affords researchers to pursue more powerful
comput...
Few-shot learning (FSL) is the process of rapid generalization from abun...
Recognizing new objects by learning from a few labeled examples in an
ev...
Self-supervised learning provides an opportunity to explore unlabeled ch...
Pre-training visual and textual representations from large-scale image-t...
Many segmentation tasks for biomedical images can be modeled as the
mini...
Deep Neural Networks (DNNs), despite their tremendous success in recent
...
In clinical applications, neural networks must focus on and highlight th...
The recent state-of-the-art deep learning methods have significantly imp...
Three-dimensional medical image segmentation is one of the most importan...
Brain Tumor Segmentation from magnetic resonance imaging (MRI) is a crit...
We present and evaluate a new deep neural network architecture for autom...
Accurately predicting and detecting interstitial lung disease (ILD) patt...
Computed tomography imaging is a standard modality for detecting and
ass...
Remarkable progress has been made in image recognition, primarily due to...