Related papers: MutexMatch: Semi-Supervised Learning with Mutex-Ba…

Semi-supervised learning (SSL) has made significant strides in the field of remote sensing. Finding a large number of labeled datasets for SSL methods is uncommon, and manually labeling datasets is expensive and time-consuming. Furthermore,…

Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…

Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction…

Semi-Supervised Learning (SSL) is fundamentally a missing label problem, in which the label Missing Not At Random (MNAR) problem is more realistic and challenging, compared to the widely-adopted yet naive Missing Completely At Random…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Medical image classification is a challenging task due to the scarcity of labeled samples and class imbalance caused by the high variance in disease prevalence. Semi-supervised learning (SSL) methods can mitigate these challenges by…

In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning. We notice that most existing consistency-based approaches suffer from overfitting and limited model generalization ability, especially when…

Recent state-of-the-art method FlexMatch firstly demonstrated that correctly estimating learning status is crucial for semi-supervised learning (SSL). However, the estimation method proposed by FlexMatch does not take into account…

While significant advances exist in pseudo-label generation for semi-supervised semantic segmentation, pseudo-label selection remains understudied. Existing methods typically use fixed confidence thresholds to retain high-confidence…

Medical image segmentation is a fundamental and critical step in many clinical approaches. Semi-supervised learning has been widely applied to medical image segmentation tasks since it alleviates the heavy burden of acquiring…

Self-Supervised Learning (SSL) is crucial for real-world applications, especially in data-hungry domains such as healthcare and self-driving cars. In addition to a lack of labeled data, these applications also suffer from distributional…

Ethical bias in machine learning models has become a matter of concern in the software engineering community. Most of the prior software engineering works concentrated on finding ethical bias in models rather than fixing it. After finding…

Semi-supervised learning (SSL) is a widely used technique in scenarios where labeled data is scarce and unlabeled data is abundant. While SSL is popular for image and text classification, it is relatively underexplored for the task of…

In this work, we introduce a novel problem setup termed as Heterogeneous Semi-Supervised Learning (HSSL), which presents unique challenges by bridging the semi-supervised learning (SSL) task and the unsupervised domain adaptation (UDA)…

Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches. This paper studies whether this common practice improves learning and how. We compare it to an alternative setting where each mini-batch…

Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…

Class imbalance remains a critical challenge in semi-supervised learning (SSL), especially when distributional mismatches between labeled and unlabeled data lead to biased classification. Although existing methods address this issue by…

Semi-supervised learning on class-imbalanced data, although a realistic problem, has been under studied. While existing semi-supervised learning (SSL) methods are known to perform poorly on minority classes, we find that they still generate…

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL…

A common classification task situation is where one has a large amount of data available for training, but only a small portion is annotated with class labels. The goal of semi-supervised training, in this context, is to improve…