no code implementations • 6 Mar 2024 • Yuta Ono, Till Aczel, Benjamin Estermann, Roger Wattenhofer
Active learning is a machine learning paradigm designed to optimize model performance in a setting where labeled data is expensive to acquire.
no code implementations • 6 Mar 2024 • Paul Doucet, Benjamin Estermann, Till Aczel, Roger Wattenhofer
This study addresses the integration of diversity-based and uncertainty-based sampling strategies in active learning, particularly within the context of self-supervised pre-trained models.
no code implementations • 3 Oct 2023 • Vivian Ziemke, Benjamin Estermann, Roger Wattenhofer, Ye Wang
In the evolving landscape of digital art, Non-Fungible Tokens (NFTs) have emerged as a groundbreaking platform, bridging the realms of art and technology.
no code implementations • 7 Mar 2023 • Giacomo Camposampiero, Loic Houmard, Benjamin Estermann, Joël Mathys, Roger Wattenhofer
While artificial intelligence (AI) models have achieved human or even superhuman performance in many well-defined applications, they still struggle to show signs of broad and flexible intelligence.
1 code implementation • 2 Mar 2023 • Benjamin Estermann, Roger Wattenhofer
We compare DAVA to models with optimal hyperparameters.
1 code implementation • NeurIPS 2020 • Benjamin Estermann, Markus Marks, Mehmet Fatih Yanik
Disentanglement is at the forefront of unsupervised learning, as disentangled representations of data improve generalization, interpretability, and performance in downstream tasks.