Related papers: Robust Amortized Bayesian Inference with Self-Cons…
Bayesian optimisation for real-world problems is often performed interactively with human experts, and integrating their domain knowledge is key to accelerate the optimisation process. We consider a setup where experts provide advice on the…
Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance. In pool-based active learning, accessible unlabeled data…
Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's prediction (i.e. the pseudo-parallel data). While self-training…
Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…
Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model's discriminative…
Attribute reduction is one of the most important research topics in the theory of rough sets, and many rough sets-based attribute reduction methods have thus been presented. However, most of them are specifically designed for dealing with…
Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…
Semisupervised methods inevitably invoke some assumption that links the marginal distribution of the features to the regression function of the label. Most commonly, the cluster or manifold assumptions are used which imply that the…
Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning (SSL). The prediction uncertainty is typically expressed as the \emph{entropy} computed by the transformed…
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…
Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a…
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…
While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of…
Bayesian Neural Networks with Latent Variables (BNN+LVs) capture predictive uncertainty by explicitly modeling model uncertainty (via priors on network weights) and environmental stochasticity (via a latent input noise variable). In this…
Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…
Modern neural networks have proven to be powerful function approximators, providing state-of-the-art performance in a multitude of applications. They however fall short in their ability to quantify confidence in their predictions - this is…
A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However,…
It is well known that for some tasks, labeled data sets may be hard to gather. Therefore, we wished to tackle here the problem of having insufficient training data. We examined learning methods from unlabeled data after an initial training…
Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many…
Existing semi-supervised learning algorithms adopt pseudo-labeling and consistency regulation techniques to introduce supervision signals for unlabeled samples. To overcome the inherent limitation of threshold-based pseudo-labeling, prior…