Related papers: Interpretable Failure Detection with Human-Level C…

Despite their impressive performance, large language models (LLMs) such as ChatGPT are known to pose important risks. One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have…

Trustworthy environment perception is the fundamental basis for the safe deployment of automated agents such as self-driving vehicles or intelligent robots. The problem remains that such trust is notoriously difficult to guarantee in the…

While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and…

In order to design haptic icons or build a haptic vocabulary, we require a set of easily distinguishable haptic signals to avoid perceptual ambiguity, which in turn requires a way to accurately estimate the perceptual (dis)similarity of…

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

Scientists form hypotheses and experimentally test them. If a hypothesis fails (is refuted), scientists try to explain the failure to eliminate other hypotheses. The more precise the failure analysis the more hypotheses can be eliminated.…

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

Semantic segmentation is an essential component of medical image analysis research, with recent deep learning algorithms offering out-of-the-box applicability across diverse datasets. Despite these advancements, segmentation failures remain…

As mobile robots are increasingly deployed in human environments, enabling them to predict how people perceive them is critical for socially adaptable navigation. Predicting perceptions is challenging for two main reasons: (1) HRI…

Penalized likelihood models are widely used to simultaneously select variables and estimate model parameters. However, the existence of weak signals can lead to inaccurate variable selection, biased parameter estimation, and invalid…

Suicidal ideation detection is critical for real-time suicide prevention, yet its progress faces two under-explored challenges: limited language coverage and unreliable annotation practices. Most available datasets are in English, but even…

Understanding the decision-making process of machine learning models provides valuable insights into the task, the data, and the reasons behind a model's failures. In this work, we propose a method that performs inherently interpretable…

The advancement of Large Language Models (LLMs) has greatly improved our ability to process complex language. However, accurately detecting logical fallacies remains a significant challenge. This study presents a novel and effective prompt…

Reliably assessing model confidence in deep learning and predicting errors likely to be made are key elements in providing safety for model deployment, in particular for applications with dire consequences. In this paper, it is first shown…

In image classification tasks, deep learning models are vulnerable to image distortions i.e. their accuracy significantly drops if the input images are distorted. An image-classifier is considered "reliable" if its accuracy on distorted…

This paper presents an automated approach for interpretable feature recommendation for solving signal data analytics problems. The method has been tested by performing experiments on datasets in the domain of prognostics where…

Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data, which are costly and impractical to obtain in clinical…

Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations. These issues, exacerbated by token limits, often cause models to miss…

Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth estimation and normal estimation. These different tasks provide…

Testing remains the primary method to evaluate the accuracy of neural network perception systems. Prior work on the formal verification of neural network perception models has been limited to notions of local adversarial robustness for…