Related papers: Concept Identification for Complex Engineering Dat…

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…

To improve the trustworthiness of an AI model, finding consistent, understandable representations of its inference process is essential. This understanding is particularly important in high-stakes operations such as weather forecasting,…

Good software documentation encourages good software engineering, but the meaning of "good" documentation is vaguely defined in the software engineering literature. To clarify this ambiguity, we draw on work from the data and information…

Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets due to two inconsistencies among detection datasets: taxonomy…

Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves…

Evaluating competing systems in a comparable way, i.e., benchmarking them, is an undeniable pillar of the scientific method. However, system performance is often summarized via a small number of metrics. The analysis of the evaluation…

Machine learning (ML) represents an efficient and popular approach for network traffic classification. However, network traffic classification is a challenging domain, and trained models may degrade soon after deployment due to the obsolete…

Process mining offers techniques to exploit event data by providing insights and recommendations to improve business processes. The growing amount of algorithms for process discovery has raised the question of which algorithms perform best…

Purpose: Machine learning models can only be reliably evaluated if training, validation, and test data splits are representative and not affected by the absence of classes of interest. Surgical workflow and instrument recognition tasks are…

Two fundamental challenges face generative models in engineering applications: the acquisition of high-performing, diverse datasets, and the adherence to precise constraints in generated designs. We propose a novel approach combining…

Artefacts play a vital role in software and systems development processes. Other terms like documents, deliverables, or work products are widely used in software development communities instead of the term artefact. In the following, we use…

Despite progress in vision-based inspection algorithms, real-world industrial challenges -- specifically in data availability, quality, and complex production requirements -- often remain under-addressed. We introduce the VISION Datasets, a…

A good process model is expected not only to reflect the behavior of the process, but also to be as easy to read and understand as possible. Because preferences vary across different applications, numerous measures provide ways to reflect…

When machine learning supports decision-making in safety-critical systems, it is important to verify and understand the reasons why a particular output is produced. Although feature importance calculation approaches assist in…

Streaming sources of data are becoming more common as the ability to collect data in real-time grows. A major concern in dealing with data streams is concept drift, a change in the distribution of data over time, for example, due to changes…

Feature extraction is a critical technology to realize the automatic transmission of feature information throughout product life cycles. As CAD models primarily capture the 3D geometry of products, feature extraction heavily relies on…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Concept drift is among the primary challenges faced by the data stream processing methods. The drift detection strategies, designed to counteract the negative consequences of such changes, often rely on analyzing the problem metafeatures.…

The customization of text-to-image models has seen significant advancements, yet generating multiple personalized concepts remains a challenging task. Current methods struggle with attribute leakage and layout confusion when handling…

Concept-based explanation methods, such as concept bottleneck models (CBMs), aim to improve the interpretability of machine learning models by linking their decisions to human-understandable concepts, under the critical assumption that such…