1 code implementation • 13 Feb 2024 • Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning.
1 code implementation • 9 Feb 2024 • Florian Peter Busch, Roshni Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting, Martin Mundt
A dataset is confounded if it is most easily solved via a spurious correlation which fails to generalize to new data.
1 code implementation • 11 Jan 2024 • Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting
Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for inspecting the model and revising suboptimal policies.
1 code implementation • 15 Sep 2023 • Wolfgang Stammer, Felix Friedrich, David Steinmann, Manuel Brack, Hikaru Shindo, Kristian Kersting
Current AI research mainly treats explanations as a means for model inspection.
no code implementations • 25 Aug 2023 • David Steinmann, Wolfgang Stammer, Felix Friedrich, Kristian Kersting
Specifically, a CB2M learns to generalize interventions to appropriate novel situations via a two-fold memory with which it can learn to detect mistakes and to reapply previous interventions.
1 code implementation • 13 Jun 2023 • Lukas Helff, Wolfgang Stammer, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting
Despite the successes of recent developments in visual AI, different shortcomings still exist; from missing exact logical reasoning, to abstract generalization abilities, to understanding complex and noisy scenes.
1 code implementation • 16 Nov 2022 • Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbacher, Dwarak Vittal, Kristian Kersting
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases.
1 code implementation • 19 Oct 2022 • Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
In this work, we question the current common practice of storing all information in the model parameters and propose the Revision Transformer (RiT) to facilitate easy model updating.
3 code implementations • 4 Mar 2022 • Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
In addition, we discuss existing and introduce novel measures and benchmarks for evaluating the overall abilities of a XIL method.
1 code implementation • CVPR 2022 • Wolfgang Stammer, Marius Memmel, Patrick Schramowski, Kristian Kersting
In this work, we show the advantages of prototype representations for understanding and revising the latent space of neural concept learners.
no code implementations • 7 Oct 2021 • Arseny Skryagin, Wolfgang Stammer, Daniel Ochs, Devendra Singh Dhami, Kristian Kersting
The probability estimates resulting from NPPs act as the binding element between the logical program and raw input data, thereby allowing SLASH to answer task-dependent logical queries.
3 code implementations • CVPR 2021 • Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space.
1 code implementation • 15 Jan 2020 • Patrick Schramowski, Wolfgang Stammer, Stefano Teso, Anna Brugger, Xiaoting Shao, Hans-Georg Luigs, Anne-Katrin Mahlein, Kristian Kersting
Deep neural networks have shown excellent performances in many real-world applications.