V. Belagiannis and W. Kellermann in Stanford University’s World’s Top 2% Scientists

Symbolic picture for the article. The link opens the image in a large view.
7. October 2025

Stanford University’s World’s Top 2% Scientists list is a prestigious ranking of the top 2% of the most-cited scientists worldwide across all disciplines. It is published annually in collaboration with Elsevier and based on data from Scopus. The latest edition was released in August 2025.
We are delighted to announce that Prof. Dr. Vasileios Belagiannis and Prof. Dr.-Ing. Walter Kellermann from our Chair have been included in this renowned ranking.
Congratulations to both!
This recognition is a proof to our group’s dedication to conducting state-of-the-art research that pushes the boundaries of machine learning and signal processing. Our focus on fundamental challenges and innovative solutions is reflected in our recent publications. Below is a selection of our latest work that showcases our commitment to academic excellence:

  1. “Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection”
    Authors: Marc Hölle, Walter Kellermann, Vasileios Belagiannis
    This work introduces a method for semantic segmentation models to better identify unknown objects in complex scenes, such as autonomous driving, by explicitly accounting for uncertainty.
  2. “Revisiting Gradient-Based Uncertainty for Monocular Depth Estimation”
    Authors: Julia Hornauer, Amir El-Ghoussani, Vasileios Belagiannis
    This paper presents a simple and effective post-hoc method to assess pixel-wise uncertainty in depth estimation models, which is crucial for safety-critical applications.
  3. “Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation“

    4. Authors: Michele De Vita, Vasileios Belagiannis
    Addressing a key limitation in generative modeling, this research proposes a way to quantify pixel-wise uncertainty during the image generation process of diffusion models to improve sample quality.

  4. “Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature”
    Authors: Rohan Asthana, Joschua Conrad, Maurits Ortmanns, Vasileios Belagiannis
    This publication introduces a novel and efficient zero-cost proxy for Neural Architecture Search (NAS) that eliminates the need for labeled data by leveraging properties of network layer features and output curvature.

Source:

1. https://top2percentscientists.com
2. https://elsevier.digitalcommonsdata.com/datasets/btchxktzyw/7

Category: Chair