no code implementations • 15 May 2024 • Johannes Jakubik, Michael Vössing, Manil Maskey, Christopher Wölfle, Gerhard Satzger
Therefore, we develop a range of novel, model-agnostic algorithms for Uncertainty Quantification-Based Label Error Detection (UQ-LED), which combine the techniques of confident learning (CL), Monte Carlo Dropout (MCD), model uncertainty measures (e. g., entropy), and ensemble learning to enhance label error detection.
1 code implementation • 21 Mar 2024 • Patrick Hemmer, Max Schemmer, Niklas Kühl, Michael Vössing, Gerhard Satzger
Our work provides researchers with a theoretical foundation of complementarity in human-AI decision-making and demonstrates that leveraging sources of complementarity potential constitutes a viable pathway toward effective human-AI collaboration.
no code implementations • 9 Jan 2024 • Philipp Spitzer, Joshua Holstein, Patrick Hemmer, Michael Vössing, Niklas Kühl, Dominik Martin, Gerhard Satzger
In this work, we explore the effects of providing contextual information on human decisions to delegate instances to an AI.
3 code implementations • 5 Dec 2023 • Simeon Allmendinger, Patrick Hemmer, Moritz Queisner, Igor Sauer, Leopold Müller, Johannes Jakubik, Michael Vössing, Niklas Kühl
We demonstrate the usage of state-of-the-art text-to-image architectures in the context of laparoscopic imaging with regard to the surgical removal of the gallbladder as an example.
1 code implementation • 16 Nov 2023 • Leopold Müller, Patrick Hemmer, Moritz Queisner, Igor Sauer, Simeon Allmendinger, Johannes Jakubik, Michael Vössing, Niklas Kühl
A significant challenge in image-guided surgery is the accurate measurement task of relevant structures such as vessel segments, resection margins, or bowel lengths.
1 code implementation • 6 Jul 2023 • Johannes Jakubik, Daniel Weber, Patrick Hemmer, Michael Vössing, Gerhard Satzger
Hence, human-in-the-loop (HITL) extensions to ML models add a human review for instances that are difficult to classify.
1 code implementation • NeurIPS 2023 • Benedikt Blumenstiel, Johannes Jakubik, Hilde Kühne, Michael Vössing
To address this problem, zero-shot semantic segmentation makes use of large self-supervised vision-language models, allowing zero-shot transfer to unseen classes.
no code implementations • 19 Apr 2023 • Philipp Spitzer, Joshua Holstein, Michael Vössing, Niklas Kühl
With the increased adoption of artificial intelligence (AI) in industry and society, effective human-AI interaction systems are becoming increasingly important.
1 code implementation • 14 Apr 2023 • Patrick Hemmer, Lukas Thede, Michael Vössing, Johannes Jakubik, Niklas Kühl
In this paper, we propose a three-step approach to reduce the number of expert predictions required to train learning to defer algorithms.
no code implementations • 16 Mar 2023 • Patrick Hemmer, Monika Westphal, Max Schemmer, Sebastian Vetter, Michael Vössing, Gerhard Satzger
In an experimental study with 196 participants, we show that task performance and task satisfaction improve through AI delegation, regardless of whether humans are aware of the delegation.
no code implementations • 23 Jan 2023 • Johannes Jakubik, Michal Muszynski, Michael Vössing, Niklas Kühl, Thomas Brunschwiler
However, DL-based approaches are designed for one specific task in a single geographic region based on specific frequency bands of satellite data.
no code implementations • 22 Dec 2022 • Johannes Jakubik, Michael Vössing, Niklas Kühl, Jannis Walk, Gerhard Satzger
Data-centric artificial intelligence (data-centric AI) represents an emerging paradigm emphasizing that the systematic design and engineering of data is essential for building effective and efficient AI-based systems.
1 code implementation • 14 Jul 2022 • Johannes Jakubik, Benedikt Blumenstiel, Michael Vössing, Patrick Hemmer
Few-shot learning addresses this challenge and reduces data gathering and labeling costs by learning novel classes with very few labeled data.
1 code implementation • 16 Jun 2022 • Patrick Hemmer, Sebastian Schellhammer, Michael Vössing, Johannes Jakubik, Gerhard Satzger
In this work, we propose an approach that trains a classification model to complement the capabilities of multiple human experts.
no code implementations • 10 May 2022 • Max Schemmer, Patrick Hemmer, Maximilian Nitsche, Niklas Kühl, Michael Vössing
However, we find no effect of explanations on users' performance compared to sole AI predictions.
no code implementations • 3 May 2022 • Patrick Hemmer, Max Schemmer, Niklas Kühl, Michael Vössing, Gerhard Satzger
Over the last years, the rising capabilities of artificial intelligence (AI) have improved human decision-making in many application areas.
no code implementations • 19 Apr 2022 • Patrick Hemmer, Max Schemmer, Lara Riefle, Nico Rosellen, Michael Vössing, Niklas Kühl
Recent developments in Artificial Intelligence (AI) have fueled the emergence of human-AI collaboration, a setting where AI is a coequal partner.
no code implementations • 23 Apr 2021 • Patrick Zschech, Jannis Walk, Kai Heinrich, Michael Vössing, Niklas Kühl
For this purpose, we consider the design of such systems from a hybrid intelligence (HI) perspective and aim to derive prescriptive design knowledge for CV-based HI systems.