← Search

Markus Käppeler

2 accepted papers

2025

A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation

RA-L 2025

A key challenge for the widespread application of learning-based models for robotic perception is to significantly reduce the required amount of annotated training data while achieving accurate predictions. This is essential not only to decrease operating costs but also to speed up deployment time.

Cited by 8SourcecodeScholar
2024

Few-Shot Panoptic Segmentation With Foundation Models

ICRA 2024poster

Current state-of-the-art methods for panoptic segmentation require an immense amount of annotated training data that is both arduous and expensive to obtain posing a significant challenge for their widespread adoption. Concurrently, recent breakthroughs in visual representation learning have sparked…

Cited by 21SourcecodeScholar