Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw
data utilization. However, its training procedure suffers from confirmation bias due to the …

Deep neural networks achieve remarkable performances on a wide range of tasks with the
aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor …

The capability of the traditional semi-supervised learning (SSL) methods is far from real-
world application due to severely biased pseudo-labels caused by (1) class imbalance and …

Deep semi-supervised learning (SSL) methods aim to take advantage of abundant
unlabeled data to improve the algorithm performance. In this paper, we consider the …

Deep neural networks usually perform poorly when the training dataset suffers from extreme
class imbalance. Recent studies found that directly training with out-of-distribution data (ie …

Self-supervised learning for semi-supervised facial expression recognition aims to avoid the
need to collect expensive labeled facial expression data. Existing methods demonstrate an …

In typical medical image classification problems labeled data is scarce while unlabeled data
is more available. Semi-supervised learning and self-supervised learning are two different …

Trained on web-scale image-text pairs, Vision-Language Models (VLMs) such as CLIP can
recognize images of common objects in a zero-shot fashion. However, it is underexplored …

Deep learning in general domains has constantly been extended to domain-specific tasks
requiring the recognition of fine-grained characteristics. However, real-world applications for …

In this work, we propose Reciprocal Distribution Alignment (RDA) to address semi-
supervised learning (SSL), which is a hyperparameter-free framework that is independent of …