Multifunctional Biomaterials

Photo: Foltan/ATB

Project

Title
Erforschung und Erweiterung von Computer Vision Foundation Models (ExploRing and Expanding the FrontierRs of FoundAtion ModEls)
Acronym
REFRAME
Start
01.10.2024
End
30.09.2027
Coordinating Institute
Fraunhofer Heinrich Hertz Institut
Partner
Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
Bergische Universität Wuppertal

Summary
In the field of computer vision, Vision Foundation Models (VFM) have set new standards in visual tasks for understanding visual data, e.g. for image and object recognition, segmentation and classification, e.g. CLIP, SAM, SEEM. Despite the progress of VFM, crucial questions remain about the trustworthiness of these models. It is unclear when a model leaves the domain of its training It is unclear when a model leaves the range of its training data and how the accuracy behaves across different domains or how the accuracy is changed by adaptation and fine-tuning. REFRAME addresses these open questions. The overall goal is to achieve a sustainable, robust, flexible and efficient use of VFM in specific tasks. To this end, it is essential 1) to develop methods to investigate their limitations and identify uncertainties in the predictions and to provide them to users and 2) to increase the trustworthiness and explainability through appropriate methods, e.g. to recognise and reduce biases, and 3) to develop resilient and efficient methodologies to adapt VFM to specific domains and tasks even with little data. We focus on some important aspects and the associated method development that will help to strengthen confidence and reliability in the predictions of VFM and the models based on them. T

Funding
Bundesministerium für Bildung und Forschung (BMBF)
Funding agency
Deutsches Zentrum für Luft- und Raumfahrt (DLR)
Grant agreement number
01IS24073B
Funding framework
Richtlinie zur Förderung von Forschungsprojekten zum Thema „Flexible, resiliente und effiziente Machine-Learning-Modelle“, Bundesanzeiger vom 07.09.2023

Cookies

We use cookies. Some are required to offer you the best possible content and functions while others help us to anonymously analyze access to our website. (Matomo) Privacy policy

Required required

Necessary cookies are absolutely essential for the proper functioning of the website. This category only includes cookies that ensure basic functionalities and security features of the website. These cookies do not store any personal information.

Cookie Duration Description
PHPSESSID Session Stores your current session with reference to PHP applications, ensuring that all features of the site can be displayed properly. The cookie is deleted when the browser is closed.
bakery 24 hours Stores your cookie preferences.
fe_typo_user Session Is used to identify a session ID when logging into the TYPO3 frontend.
__Secure-typo3nonce_xxx Session Security-related. For internal use by TYPO3.
Analytics

With cookies in this category, we learn from visitors' behavior on our website and can make relevant information even more accessible.

Cookie Duration Description
_pk_id.xxx 13 months Matomo - User ID (for anonymous statistical analysis of visitor traffic; determines which user is being tracked)
_pk_ses.xxx 30 minutes Matomo - Session ID (for anonymous statistical analysis of visitor traffic; determines which session is being tracked)