Skip to content
Technical University of Munich

Veranstaltungen

Explainability and Compositionality for Visual Recognition with Minimal Supervision

SAP, Veranstaltung |

Zeynep Akata is going to talk about her work on Zero-Shot Learning and Explainable Machine Learning, focusing on learning compositional representations of images, generating images and visual features using natural language descriptions, and explaining classification decisions to end-users.

Speaker: Prof. Dr. Zeynep Akata

Date: 18.03.2025,14:00-15:00

Location: SAP Labs Munich (MUE03), Friedrich-Ludwig-Bauer-Straße 5, 85748 Garching bei München, Auditorium (AE.76)

SignUp: https://events.sap.com/de/applied-research-talk-ak/en/registration.aspx

Abstract: Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. In this talk, I will present my past and current work on Zero-Shot Learning and Explainable Machine Learning combining vision and language where we show (1) how to learn compositional representations of images that go beyond recognition towards understanding, (2) how to generate images and visual features using natural language descriptions for fine-grained low-shot learning scenarios, and (3) how our models focus on discriminating properties of the visible object, jointly predict a class label, explain why/not the predicted label is chosen for the image.

Bio: Zeynep Akata is a Liesel Beckmann Distinguished Professor of Computer Science at the Technical University of Munich and the Director of the Institute for Explainable Machine Learning at Helmholtz Munich. Before she joined TUM in January 2024, she was a professor of computer science (W3) within the Cluster of Excellence Machine Learning at the University of Tübingen, a senior group leader at the MPI-Inf and a senior researcher at the MPI-IS. After completing her PhD at the INRIA Rhone Alpes (2014), she worked as a post-doctoral researcher at the MPI for Informatics (2014-17) and at UC Berkeley (2016-17) and as an assistant professor at the University of Amsterdam (2017-19). She received a Lise-Meitner Award for Excellent Women in Computer Science from the Max Planck Society in 2014, an ERC Starting Grant in 2019, the German Pattern Recognition Award in 2021, the ECVA Young Researcher Award in 2022, the Young Researcher award from the Alfried Krupp Foundation in 2023 and she was named as one of Germany’s Top 40 Under 40 in 2024. Her research interests include multimodal learning and explainable AI.

◄ Back to: Events
To top