Related papers: PG-LBO: Enhancing High-Dimensional Bayesian Optimi…

Recently, several Bayesian deep learning methods have been proposed for semi-supervised medical image segmentation. Although they have achieved promising results on medical benchmarks, some problems are still existing. Firstly, their…

This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses…

Optimization of product and system characteristics is required in many fields, including design and control. Bayesian optimization (BO) is often used when there are high observing costs, because BO theoretically guarantees an upper bound on…

Most of the data-driven approaches applied to bearing fault diagnosis up to date are established in the supervised learning paradigm, which usually requires a large set of labeled data collected a priori. In practical applications, however,…

The premise of semi-supervised learning (SSL) is that combining labeled and unlabeled data yields significantly more accurate models. Despite empirical successes, the theoretical understanding of SSL is still far from complete. In this…

This paper concerns pseudo labelling in segmentation. Our contribution is fourfold. Firstly, we present a new formulation of pseudo-labelling as an Expectation-Maximization (EM) algorithm for clear statistical interpretation. Secondly, we…

While supervised deep learning has achieved great success in a range of applications, relatively little work has studied the discovery of knowledge from unlabeled data. In this paper, we propose an unsupervised deep learning framework to…

Gaussian processes are the model of choice in Bayesian optimization and active learning. Yet, they are highly dependent on cleverly chosen hyperparameters to reach their full potential, and little effort is devoted to finding good…

While deep neural networks have been shown to perform remarkably well in many machine learning tasks, labeling a large amount of ground truth data for supervised training is usually very costly to scale. Therefore, learning robust…

3D segmentation is a core problem in computer vision and, similarly to many other dense prediction tasks, it requires large amounts of annotated data for adequate training. However, densely labeling 3D point clouds to employ…

Bayesian Optimization (BO) methods are useful for optimizing functions that are expen- sive to evaluate, lack an analytical expression and whose evaluations can be contaminated by noise. These methods rely on a probabilistic model of the…

We present a method to improve the calibration of deep ensembles in the small training data regime in the presence of unlabeled data. Our approach is extremely simple to implement: given an unlabeled set, for each unlabeled data point, we…

Bayesian optimization has attracted huge attention from diverse research areas in science and engineering, since it is capable of efficiently finding a global optimum of an expensive-to-evaluate black-box function. In general, a…

Large graph datasets make training graph neural networks (GNNs) computationally costly. Graph condensation methods address this by generating small synthetic graphs that approximate the original data. However, existing approaches rely on…

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…

In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned…

Gaussian processes (GPs), implemented through multivariate Gaussian distributions for a finite collection of data, are the most popular approach in small-area spatial statistical modelling. In this context they are used to encode…

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

Pre-trained code models have recently achieved substantial improvements in many code intelligence tasks. These models are first pre-trained on large-scale unlabeled datasets in a task-agnostic manner using self-supervised learning, and then…