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.
no code implementations • 3 Oct 2023 • Max Schemmer, Andrea Bartos, Philipp Spitzer, Patrick Hemmer, Niklas Kühl, Jonas Liebschner, Gerhard Satzger
We hypothesize that, in addition to the mental model, human learning is a key mediator of appropriate reliance and, thus, CTP.
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 • 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.
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 • 14 Apr 2022 • Max Schemmer, Patrick Hemmer, Niklas Kühl, Carina Benz, Gerhard Satzger
However, recent work has shown that AI advice is not always beneficial, as humans have shown to be unable to ignore incorrect AI advice, essentially representing an over-reliance on AI.
no code implementations • 18 Oct 2021 • Patrick Hemmer, Niklas Kühl, Jakob Schöffer
Computer-generated imagery of car models has become an indispensable part of car manufacturers' advertisement concepts.
2 code implementations • 22 Jul 2020 • Patrick Hemmer, Niklas Kühl, Jakob Schöffer
By replacing the softmax standard output of a CNN with the parameters of a Dirichlet density, the model learns to identify data instances that contribute efficiently to improving model performance during training.