Deep neural networks (DNNs) often produce overconfident out-of-distribution predictions, motivating Bayesian uncertainty quantification.The Linearized Laplace Approximation (LLA) achieves this by linearizing the DNN and applying Laplace inference to the resulting model.Importantly, the linear model is also used for prediction.We argue this linearization in the posterior may degrade fidelity to the true Laplace approximation.To alleviate this problem, without increasing significantly the computational cost, we propose the Quadratic Laplace Approximation (QLA).QLA approximates each second order factor in the approximate Laplace log-posterior using a rank-one factor obtained via efficient power iterations.QLA is expected to yield a posterior precision closer to that of the full Laplace without forming the full Hessian, which is typically intractable.For prediction, QLA also uses the linearized model.Empirically, QLA yields modest yet consistent uncertainty estimation improvements over LLA on five regression datasets.

Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools for model development, evaluation, and comparison, which hinders reproducibility and accessibility. To address this, we present torchmil , an open-source Python library built on PyTorch. torchmil offers a unified, modular, and extensible framework, featuring basic building blocks for MIL models, a standardized data format, and a curated collection of benchmark datasets and models. The library includes comprehensive documentation and tutorials to support both practitioners and researchers. torchmil aims to accelerate progress in MIL and lower the entry barrier for new users. Available at https://torchmil.readthedocs.io .

The Multiple Instance Learning (MIL) paradigm is attracting plenty of attention in medical imaging classification, where labeled data is scarce. MIL methods cast medical images as bags of instances (e.g. patches in whole slide images, or slices in CT scans), and only bag labels are required for training. Deep MIL approaches have obtained promising results by aggregating instance-level representations via an attention mechanism to compute the bag-level prediction. These methods typically capture both local interactions among adjacent instances and global, long-range dependencies through various mechanisms. However, they treat attention values deterministically, potentially overlooking uncertainty in the contribution of individual instances. In this work we propose a novel probabilistic framework that estimates a probability distribution over the attention values, and accounts for both global and local interactions. In a comprehensive evaluation involving eleven state-of-the-art baselines and three medical datasets, we show that our approach achieves top predictive performance in different metrics. Moreover, the probabilistic treatment of the attention provides uncertainty maps that are interpretable in terms of illness localization.

Multiple Instance Learning (MIL) is widely used in medical imaging classification to reduce the labeling effort. While only bag labels are available for training, one typically seeks predictions at both bag and instance levels (classification and localization tasks, respectively). Early MIL methods treated the instances in a bag independently. Recent methods account for global and local dependencies among instances. Although they have yielded excellent results in classification, their performance in terms of localization is comparatively limited. We argue that these models have been designed to target the classification task, while implications at the instance level have not been deeply investigated. Motivated by a simple observation -- that neighboring instances are likely to have the same label -- we propose a novel, principled, and flexible mechanism to model local dependencies. It can be used alone or combined with any mechanism to model global dependencies (e.g., transformers). A thorough empirical validation shows that our module leads to state-of-the-art performance in localization while being competitive or superior in classification. Our code is at https://github.com/Franblueee/SmMIL.

Multiple Instance Learning (MIL) is a weakly supervised paradigm that has been successfully applied to many different scientific areas and is particularly well suited to medical imaging. Probabilistic MIL methods, and more specifically Gaussian Processes (GPs), have achieved excellent results due to their high expressiveness and uncertainty quantification capabilities. One of the most successful GP-based MIL methods, VGPMIL, resorts to a variational bound to handle the intractability of the logistic function. Here, we formulate VGPMIL using Pólya-Gamma random variables. This approach yields the same variational posterior approximations as the original VGPMIL, which is a consequence of the two representations that the Hyperbolic Secant distribution admits. This leads us to propose a general GP-based MIL method that takes different forms by simply leveraging distributions other than the Hyperbolic Secant one. Using the Gamma distribution we arrive at a new approach that obtains competitive or superior predictive performance and efficiency. This is validated in a comprehensive experimental study including one synthetic MIL dataset, two well-known MIL benchmarks, and a real-world medical problem. We expect that this work provides useful ideas beyond MIL that can foster further research in the field.

Multiple instance learning (MIL) is a weakly supervised learning paradigm that is becoming increasingly popular because it requires less labeling effort than fully supervised methods. This is especially interesting for areas where the creation of large annotated datasets remains challenging, as in medicine. Although recent deep learning MIL approaches have obtained state-of-the-art results, they are fully deterministic and do not provide uncertainty estimations for the predictions. In this work, we introduce the attention Gaussian process (AGP) model, a novel probabilistic attention mechanism based on Gaussian processes (GPs) for deep MIL. AGP provides accurate bag-level predictions as well as instance-level explainability and can be trained end-to-end. Moreover, its probabilistic nature guarantees robustness to overfit on small datasets and uncertainty estimations for the predictions. The latter is especially important in medical applications, where decisions have a direct impact on the patient's health. The proposed model is validated experimentally as follows. First, its behavior is illustrated in two synthetic MIL experiments based on the well-known MNIST and CIFAR-10 datasets, respectively. Then, it is evaluated in three different real-world cancer detection experiments. AGP outperforms state-of-the-art MIL approaches, including deterministic deep learning ones. It shows a strong performance even on a small dataset with less than 100 labels and generalizes better than competing methods on an external test set. Moreover, we experimentally show that predictive uncertainty correlates with the risk of wrong predictions, and therefore it is a good indicator of reliability in practice. Our code is publicly available.

Medical image segmentation is a challenging task, particularly due to inter- and intra-observer variability, even between medical experts. In this paper, we propose a novel model, called Probabilistic Inter-Observer and iNtra-Observer variation NetwOrk (Pionono). It captures the labeling behavior of each rater with a multidimensional probability distribution and integrates this information with the feature maps of the image to produce probabilistic segmentation predictions. The model is optimized by variational inference and can be trained end-to-end. It outperforms state-of-the-art models such as STAPLE, Probabilistic U-Net, and models based on confusion matrices. Additionally, Pionono predicts multiple coherent segmentation maps that mimic the rater’s expert opinion, which provides additional valuable information for the diagnostic process. Experiments on real-world cancer segmentation datasets demonstrate the high accuracy and efficiency of Pionono, making it a powerful tool for medical image analysis.

Learning structures between groups of variables from data with missing values is an important task in the real world, yet difficult to solve. One typical scenario is discovering the structure among topics in the education domain to identify learning pathways. Here, the observations are student performances for questions under each topic which contain missing values. However, most existing methods focus on learning structures between a few individual variables from the complete data. In this work, we propose VISL, a novel scalable structure learning approach that can simultaneously infer structures between groups of variables under missing data and perform missing value imputations with deep learning. Particularly, we propose a generative model with a structured latent space and a graph neural network-based architecture, scaling to a large number of variables. Empirically, we conduct extensive experiments on synthetic, semi-synthetic, and real-world education data sets. We show improved performances on both imputation and structure learning accuracy compared to popular and recent approaches.

This paper introduces deep Gaussian processes (DGPs) for geo-physical parameter retrieval. Unlike the standard full GP model, the DGP accounts for complicated (modular, hierarchical) processes, provides a efficient solution that scales well to large datasets, and improves prediction accuracy over standard full and sparse GP models. We give empirical evidence of performance for estimation of surface dew point temperature from infrared sounding data.

Current remote sensing image classification problems have to deal with an unprecedented amount of heterogeneous and complex data sources. Upcoming missions will soon provide large data streams that will make land cover/use classification difficult. Machine-learning classifiers can help at this, and many methods are currently available. A popular kernel classifier is the Gaussian process classifier (GPC), since it approaches the classification problem with a solid probabilistic treatment, thus yielding confidence intervals for the predictions as well as very competitive results to the state-of-the-art neural networks and support vector machines. However, its computational cost is prohibitive for large-scale applications, and constitutes the main obstacle precluding wide adoption. This paper tackles this problem by introducing two novel efficient methodologies for GP classification. We first include the standard random Fourier features approximation into GPC, which largely decreases its computational cost and permits large-scale remote sensing image classification. In addition, we propose a model which avoids randomly sampling a number of Fourier frequencies and alternatively learns the optimal ones within a variational Bayes approach. The performance of the proposed methods is illustrated in complex problems of cloud detection from multispectral imagery and infrared sounding data. Excellent empirical results support the proposal in both computational cost and accuracy.

Passive Millimeter Wave Images (PMMWIs) are being increasingly used to identify and localize objects concealed under clothing. Taking into account the quality of these images and the unknown position, shape, and size of the hidden objects, large data sets are required to build successful classification/detection systems. Kernel methods, in particular Gaussian Processes (GPs), are sound, flexible, and popular techniques to address supervised learning problems. Unfortunately, their computational cost is known to be prohibitive for large scale applications. In this work, we present a novel approach to PMMWI classification based on the use of Gaussian Processes for large data sets. The proposed methodology relies on linear approximations to kernel functions through random Fourier features. Model hyperparameters are learned within a variational Bayes inference scheme. Our proposal is well suited for real-time applications, since its computational cost at training and test times is much lower than the original GP formulation. The proposed approach is tested on a unique, large, and real PMMWI database containing a broad variety of sizes, types, and locations of hidden objects.

This paper presents an efficient methodology for approximating kernel functions in Gaussian process classification (GPC). Two models are introduced. We first include the standard random Fourier features (RFF) approximation into GPC, which largely improves the computational efficiency and permits large scale remote sensing data classification. In addition, we develop a novel approach which avoids randomly sampling a number of Fourier frequencies, and alternatively learns the optimal ones using a variational Bayes approach. The performance of the proposed methods is illustrated in complex problems of cloud detection from multispectral imagery.