no code implementations • 18 Mar 2024 • Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Glöckler, Alex Bäuerle, Timo Ropinski
Recent advances in text-to-image synthesis enabled through a combination of language and vision foundation models have led to a proliferation of the tools available and an increased attention to the field.
1 code implementation • 18 Dec 2023 • Syeda Nahida Akter, Zichun Yu, Aashiq Muhamed, Tianyue Ou, Alex Bäuerle, Ángel Alexander Cabrera, Krish Dholakia, Chenyan Xiong, Graham Neubig
The recently released Google Gemini class of models are the first to comprehensively report results that rival the OpenAI GPT series across a wide variety of tasks.
no code implementations • 20 Jun 2022 • Alex Bäuerle, Daniel Jönsson, Timo Ropinski
Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing high activation values to reveal interesting features on a neuron level.
no code implementations • 18 Feb 2022 • Alex Bäuerle, Ángel Alexander Cabrera, Fred Hohman, Megan Maher, David Koski, Xavier Suau, Titus Barik, Dominik Moritz
Interfaces for machine learning (ML), information and visualizations about models or data, can help practitioners build robust and responsible ML systems.
1 code implementation • 17 Jan 2022 • Alex Bäuerle, Aybuke Gul Turker, Ken Burke, Osman Aka, Timo Ropinski, Christina Greer, Mani Varadarajan
With our approach, different models and datasets for large label spaces can be systematically and visually analyzed and compared to make informed fairness assessments tackling problematic bias.
no code implementations • 5 Mar 2021 • Osman Aka, Ken Burke, Alex Bäuerle, Christina Greer, Margaret Mitchell
By treating a classification model's predictions for a given image as a set of labels analogous to a bag of words, we rank the biases that a model has learned with respect to different identity labels.
no code implementations • 9 Dec 2020 • Alex Bäuerle, Patrick Albus, Raphael Störk, Tina Seufert, Timo Ropinski
In an empirical study, we assessed 37 subjects in a between-subjects design to investigate the learning outcomes and cognitive load of exploRNN compared to a classic text-based learning environment.
1 code implementation • 11 Feb 2019 • Alex Bäuerle, Christian van Onzenoodt, Timo Ropinski
To convey neural network architectures in publications, appropriate visualizations are of great importance.
1 code implementation • 9 Aug 2018 • Alex Bäuerle, Heiko Neumann, Timo Ropinski
We thus propose a novel approach that uses the power of pretrained classifiers to visually guide users to noisy labels, and let them interactively check error candidates, to iteratively improve the training data set.