Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models
Mario Döbler, Robert A. Marsden, Tobias Raichle +1
In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models…
cs.CV2021
Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
Robert A. Marsden, Alexander Bartler, Mario Döbler +1
Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to genera…