OpenDAS: Domain Adaptation for Open-Vocabulary Segmentation

G Yilmaz, S Peng, F Engelmann, M Pollefeys… - arXiv preprint arXiv …, 2024 - arxiv.org
The advent of Vision Language Models (VLMs) transformed image understanding from
closed-set classifications to dynamic image-language interactions, enabling open …
相关文章

OpenDAS: Domain Adaptation for Open-Vocabulary Segmentation

G Yilmaz, S Peng, F Engelmann, M Pollefeys… - arXiv e …, 2024 - ui.adsabs.harvard.edu
Abstract The advent of Vision Language Models (VLMs) transformed image understanding
from closed-set classifications to dynamic image-language interactions, enabling open …