The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the
limited labeled data and massive unlabeled data to improve the model's generalization …

For medical image segmentation, contrastive learning is the dominant practice to improve
the quality of visual representations by contrasting semantically similar and dissimilar pairs …

While long-tailed semi-supervised learning (LTSSL) has received tremendous attention in
many real-world classification problems, existing LTSSL algorithms typically assume that the …

Medical data often exhibits long-tail distributions with heavy class imbalance, which
naturally leads to difficulty in classifying the minority classes (ie, boundary regions or rare …

Abstract Traditional Unsupervised Domain Adaptation (UDA) leverages the labeled source
domain to tackle the learning tasks on the unlabeled target domain. It can be more …

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for
decades. The primary family of SSL algorithms, known as pseudo-labeling, involves …

Integrating high-level semantically correlated contents and low-level anatomical features is
of central importance in medical image segmentation. Towards this end, recent deep …

Abstract Contrastive Language-Image Pre-training (CLIP) has shown its ability to learn
distinctive visual representations and generalize to various downstream vision tasks …

Pseudo-label-based semi-supervised learning (SSL) algorithms trained on a class-
imbalanced set face two cascading challenges: 1) Classifiers tend to be biased towards …

Storm prediction provides the early alert for preparation, avoiding potential damage to
property and human safety. However, a traditional storm prediction model usually incurs …