Related papers: Improving Aleatoric Uncertainty Quantification in …

Graph Neural Networks (GNNs) have shown remarkable performance in the healthcare domain. However, what remained challenging is quantifying the predictive uncertainty of GNNs, which is an important aspect of trustworthiness in clinical…

Current methods for developing foundation models in medical image segmentation rely on two primary assumptions: a fixed set of classes and the immediate availability of a substantial and diverse training dataset. However, this can be…

Deep-learning methods have shown promising performance for low-dose computed tomography (LDCT) reconstruction. However, supervised methods face the problem of lacking labeled data in clinical scenarios, and the CNN-based unsupervised…

Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis. Retraining models leads to high latency and complex pipelines, which are impractical in clinical settings. The…

Model quantization is leveraged to reduce the memory consumption and the computation time of deep neural networks. This is achieved by representing weights and activations with a lower bit resolution when compared to their high precision…

To better conform to data geometry, recent deep generative modelling techniques adapt Euclidean constructions to non-Euclidean spaces. In this paper, we study normalizing flows on manifolds. Previous work has developed flow models for…

Distribution-to-distribution generative models support scientific imaging tasks ranging from modeling cellular perturbation responses to translating medical images across conditions. Trustworthy generation requires reliability, or…

Fair representation learning is an attractive approach that promises fairness of downstream predictors by encoding sensitive data. Unfortunately, recent work has shown that strong adversarial predictors can still exhibit unfairness by…

Unsupervised anomaly detection is often framed around two widely studied paradigms. Deep one-class classification, exemplified by Deep SVDD, learns compact latent representations of normality, while density estimators realized by…

Sampling from unnormalized densities presents a fundamental challenge with wide-ranging applications, from posterior inference to molecular dynamics simulations. Continuous flow-based neural samplers offer a promising approach, learning a…

Foundation models for segmentation such as the Segment Anything Model (SAM) family exhibit strong zero-shot performance, but remain vulnerable in shifted or limited-knowledge domains. This work investigates whether uncertainty…

Eliciting a high-dimensional probability distribution from an expert via noisy judgments is notoriously challenging, yet useful for many applications, such as prior elicitation and reward modeling. We introduce a method for eliciting the…

Deep neural networks have achieved significant success in the last decades, but they are not well-calibrated and often produce unreliable predictions. A large number of literature relies on uncertainty quantification to evaluate the…

Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…

Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications,…

We address the selection and evaluation of uncertain segmentation methods in medical imaging and present two case studies: prostate segmentation, illustrating that for minimal annotator variation simple deterministic models can suffice, and…

The accessibility of spatially distributed data, enabled by affordable sensors, field, and numerical experiments, has facilitated the development of data-driven solutions for scientific problems, including climate change, weather…

Segmentation is a fundamental task for extracting semantically meaningful regions from an image. The goal of segmentation algorithms is to accurately assign object labels to each image location. However, image-noise, shortcomings of…

Large annotated datasets are vital for training segmentation models, but pixel-level labeling is time-consuming, error-prone, and often requires scarce expert annotators, especially in medical imaging. In contrast, coarse annotations are…

Recently, we have witnessed great progress in the field of medical imaging classification by adopting deep neural networks. However, the recent advanced models still require accessing sufficiently large and representative datasets for…