Related papers: Designing for Ambiguity: Visual Analytics in Avala…

There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained…

Digital systems for analyzing human communication data have become prevalent in recent years. Intelligence analysis of communications data in investigative journalism, criminal intelligence, and law present particularly interesting cases,…

In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under perturbations to the…

Ante-hoc interpretability has become the holy grail of explainable artificial intelligence for high-stakes domains such as healthcare; however, this notion is elusive, lacks a widely-accepted definition and depends on the operational…

Software analytics has been the subject of considerable recent attention but is yet to receive significant industry traction. One of the key reasons is that software practitioners are reluctant to trust predictions produced by the analytics…

AI systems are increasingly governed by natural language principles, yet a key challenge arising from reliance on language remains underexplored: interpretive ambiguity. As in legal systems, ambiguity arises both from how these principles…

Alternative text is critical in communicating graphics to people who are blind or have low vision. Especially for graphics that contain rich information, such as visualizations, poorly written or an absence of alternative texts can worsen…

Predictive uncertainties in classification tasks are often a consequence of model inadequacy or insufficient training data. In popular applications, such as image processing, we are often required to scrutinise these uncertainties by…

For applications of machine learning in critical decisions, explainability is a primary concern, and often a regulatory requirement. Local linear methods for generating explanations, such as LIME and SHAP, have been criticized for being…

We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems. Specifically, we distinguish between images which lead…

Interpreting uncertain data can be difficult, particularly if the data presentation is complex. We investigate the efficacy of different modalities for representing data and how to combine the strengths of each modality to facilitate the…

Draco has been developed as an automated visualization recommendation system formalizing design knowledge as logical constraints in ASP (Answer-Set Programming). With an increasing set of constraints and incorporated design knowledge, even…

In recent years, considerable work has been devoted to explaining predictive, deep learning-based models, and in turn how to evaluate explanations. An important class of evaluation methods are ones that are human-centered, which typically…

The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate…

Supporting model interpretability for complex phenomena where annotators can legitimately disagree, such as emotion recognition, is a challenging machine learning task. In this work, we show that explicitly quantifying the uncertainty in…

Speech emotion recognition plays an important role in various applications. However, most existing approaches predict a single emotion label, oversimplifying the inherently ambiguous nature of human emotional expression. Recent large…

Understanding and communicating data uncertainty is crucial for making informed decisions in sectors like finance and healthcare. Previous work has explored how to express uncertainty in various modes. For example, uncertainty can be…

Clear presentation of uncertainty is an exception rather than rule in media articles, data-driven reports, and consumer applications, despite proposed techniques for communicating sources of uncertainty in data. This work considers, Why do…

Uncertainty is an inherent aspect of autonomous vehicle (AV) decision-making, yet it is rarely communicated to pedestrians, which hinders transparency. This study investigates how AV uncertainty can be conveyed through two approaches:…

Vision-based approaches have become the dominant paradigm for traversability estimation in unstructured outdoor environments, typically adapting vision foundation models (VFMs) via semantic segmentation supervision. However, this paradigm…