Related papers: Modeling Multimodal Aleatoric Uncertainty in Segme…

The mixture of experts (MoE) model is a versatile framework for predictive modeling that has gained renewed interest in the age of large language models. A collection of predictive ``experts'' is learned along with a ``gating function''…

We introduce a novel uncertainty-aware multimodal segmentation framework that leverages both radiological images and associated clinical text for precise medical diagnosis. We propose a Modality Decoding Attention Block (MoDAB) with a…

Collective insights from a group of experts have always proven to outperform an individual's best diagnostic for clinical tasks. For the task of medical image segmentation, existing research on AI-based alternatives focuses more on…

We introduce Mixture-of-Gaussians with Uncertainty-based Gating (MoGU), a novel Mixture-of-Experts (MoE) framework designed for regression tasks. MoGU replaces standard learned gating with an intrinsic routing paradigm where expert-specific…

Safe navigation in new environments requires autonomous vehicles and robots to accurately interpret their surroundings, relying on LiDAR scene segmentation, out-of-distribution (OOD) obstacle detection, and uncertainty computation. We…

In a distributed mixture-of-experts (MoE) system, a server collaborates with multiple specialized expert clients to perform inference. The server extracts features from input data and dynamically selects experts based on their areas of…

Lesion segmentation is inherently influenced by imaging uncertainty, arising from ill-defined lesion boundaries and inter-observer variability in diagnosis. To address this challenge, previous works formulated the multi-rater medical image…

Image segmentation is a critical step in computational biomedical image analysis, typically evaluated using metrics like the Dice coefficient during training and validation. However, in clinical settings without manual annotations,…

Despite the remarkable progress in generative modelling, current diffusion models lack a quantitative approach to assess image quality. To address this limitation, we propose to estimate the pixel-wise aleatoric uncertainty during the…

Landslides are a recurring, widespread hazard. Preparation and mitigation efforts can be aided by a high-quality, large-scale dataset that covers global at-risk areas. Such a dataset currently does not exist and is impossible to construct…

Combining multi-site data can strengthen and uncover trends, but is a task that is marred by the influence of site-specific covariates that can bias the data and therefore any downstream analyses. Post-hoc multi-site correction methods…

In safety-critical applications like medical diagnosis, certainty associated with a model's prediction is just as important as its accuracy. Consequently, uncertainty estimation and reduction play a crucial role. Uncertainty in predictions…

Image segmentation is a challenging task influenced by multiple sources of uncertainty, such as the data labeling process or the sampling of training data. In this paper we focus on binary segmentation and address these challenges using…

Aleatoric uncertainty is an intrinsic property of ill-posed inverse and imaging problems. Its quantification is vital for assessing the reliability of relevant point estimates. In this paper, we propose an efficient framework for…

In this study, we explore in depth a few under-studied topics at the intersection of uncertainty estimation and segmentation. Prior work has shown that the quality of uncertainty estimates can be very sensitive to a range of variables. As…

Medical image segmentation is a fundamental and critical step in many clinical approaches. Semi-supervised learning has been widely applied to medical image segmentation tasks since it alleviates the heavy burden of acquiring…

Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, it might not be clear from a CT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a…

Despite the recent improvements in overall accuracy, deep learning systems still exhibit low levels of robustness. Detecting possible failures is critical for a successful clinical integration of these systems, where each data point…

Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise between conflicting objectives (e.g., local editing v.s.…

Medical image segmentation is inherently uncertain. For a given image, there may be multiple plausible segmentation hypotheses, and physicians will often disagree on lesion and organ boundaries. To be suited to real-world application,…