Related papers: Do not trust what you trust: Miscalibration in Sem…

This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. The unlabeled images are usually assigned pseudo labels to be used…

Semi-supervised learning (SSL) has long been proved to be an effective technique to construct powerful models with limited labels. In the existing literature, consistency regularization-based methods, which force the perturbed samples to…

Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency…

In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled…

Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model performance. While standard SSL assumes uniform data distribution, we consider a more realistic and challenging setting called imbalanced…

Reinforcement learning (RL) has shown great success in estimating sequential treatment strategies which take into account patient heterogeneity. However, health-outcome information, which is used as the reward for reinforcement learning…

Beyond attaining domain generalization (DG), visual recognition models should also be data-efficient during learning by leveraging limited labels. We study the problem of Semi-Supervised Domain Generalization (SSDG) which is crucial for…

In this work, we revisit the semi-supervised learning (SSL) problem from a new perspective of explicitly reducing empirical distribution mismatch between labeled and unlabeled samples. Benefited from this new perspective, we first propose a…

Semi-supervised learning (SSL) arises in practice when labeled data are scarce or expensive to obtain, while large quantities of unlabeled data are readily available. With the growing adoption of machine learning techniques, it has become…

Self supervised learning (SSL) has become a very successful technique to harness the power of unlabeled data, with no annotation effort. A number of developed approaches are evolving with the goal of outperforming supervised alternatives,…

While much of recent study in semi-supervised learning (SSL) has achieved strong performance on single-label classification problems, an equally important yet underexplored problem is how to leverage the advantage of unlabeled data in…

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confidence score over a predetermined threshold. At the same time,…

Federated Learning allows the training of machine learning models by using the computation and private data resources of many distributed clients. Most existing results on Federated Learning (FL) assume the clients have ground-truth labels.…

In many contemporary applications, large amounts of unlabeled data are readily available while labeled examples are limited. There has been substantial interest in semi-supervised learning (SSL) which aims to leverage unlabeled data to…

Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior…

Pseudo-labeling (PL) and Data Augmentation-based Consistency Training (DACT) are two approaches widely used in Semi-Supervised Learning (SSL) methods. These methods exhibit great power in many machine learning tasks by utilizing unlabeled…

Pseudo-Labeling is a simple and effective approach to semi-supervised learning. It requires criteria that guide the selection of pseudo-labeled data. The latter have been shown to crucially affect pseudo-labeling's generalization…

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus…

Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these…