Learning With Limited Supervision

Learning With Limited Supervision

Learning with limited supervision encompasses various paradigms, including unsupervised, self-supervised, few-shot, and continual learning. Unsupervised and self-supervised learning address the challenge of leveraging the large availability of unlabeled data to avoid relying on labeled data, which can be time-consuming and expensive to obtain. Few-shot learning aims to acquire knowledge from a small amount of data, particularly in domains like medical applications, where traditional supervised approaches may need more samples. Continual learning focuses on preventing catastrophic forgetting, a phenomenon that occurs when updating model weights for current tasks negatively impacts performance on prior tasks. Our group primarily focuses on developing approaches utilizing these learning paradigms for image classification and segmentation, as well as video applications like panoptic segmentation or action recognition.

Recent Publications

JavaScript is required to view this publication list. If your browser does not support JavaScript, please refer to DBLP or Google Scholar for reasonably current publication lists.

Experts

  Name Contact
Dustin Carrión M.Sc.
+49 6151 16-21424
S2|02 A326
Oliver Hahn M.Sc.
+49 6151 16-21423
S2|02 A302
_
Simone Schaub-Meyer Dr. Sc.
+49 6151 16-25411
S2|02 A306
Prof. Stefan Roth, Ph.D.
+49 6151 16-21425
S2|02 A304