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

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

Confidence-aware learning is proven as an effective solution to prevent networks becoming overconfident. We present a confidence-aware camouflaged object detection framework using dynamic supervision to produce both accurate camouflage map…

The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize…

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

The interpretation of deep neural networks (DNNs) has become a key topic as more and more people apply them to solve various problems and making critical decisions. Concept-based explanations have recently become a popular approach for…

As robotic systems become increasingly integrated into real-world environments, ranging from autonomous vehicles to household assistants, they inevitably encounter diverse and unstructured scenarios that lead to failures. While such…

The crux of label-efficient semantic segmentation is to produce high-quality pseudo-labels to leverage a large amount of unlabeled or weakly labeled data. A common practice is to select the highly confident predictions as the…

Confidence estimates are often "detection-like" - driven by positive evidence in favour of a decision. This empirical observation has been interpreted as showing that human metacognition is limited by biases or heuristics. Here, we show…

A cornerstone of machine learning evaluation is the (often hidden) assumption that model and human responses are reliable enough to evaluate models against unitary, authoritative, ``gold standard'' data, via simple metrics such as accuracy,…

Data-driven methods have achieved notable performance on intent detection, which is a task to comprehend user queries. Nonetheless, they are controversial for over-confident predictions. In some scenarios, users do not only care about the…

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a…

Interpretability is crucial for ensuring RL systems align with human values. However, it remains challenging to achieve in complex decision making domains. Existing methods frequently attempt interpretability at the level of fundamental…

Credibility signals represent a wide range of heuristics typically used by journalists and fact-checkers to assess the veracity of online content. Automating the extraction of credibility signals presents significant challenges due to the…

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Flaky tests can pass or fail non-deterministically, without alterations to a software system. Such tests are frequently encountered by developers and hinder the credibility of test suites. State-of-the-art research incorporates machine…

Recent work has identified noisy and misannotated data as a core cause of hallucinations and unfaithful outputs in Natural Language Generation (NLG) tasks. Consequently, identifying and removing these examples is a key open challenge in…

State-of-the-art NLP methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors,…

Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model…

Suicide rates have risen worldwide in recent years, underscoring the urgent need for proactive prevention strategies. Social media provides valuable signals, as many at-risk individuals - who often avoid formal help due to stigma - choose…

Intensive testing using model-based approaches is the standard way of demonstrating the correctness of automotive software. Unfortunately, state-of-the-art techniques leave a crucial and labor intensive task to the test engineer:…