Spaces:
Runtime error
Request for GPU Resources for Academic Research
Hello,
this is a demo of our research paper: FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation.
FrozenSeg is a novel approach that integrates spatial knowledge from localization foundation models (e.g., SAM) with semantic knowledge from vision-language (ViL) models (e.g., CLIP). This synergistic framework is designed to enhance the precision of mask proposals for objects across an open set of categories, which is a significant challenge in the field of computer vision.
We believe that the allocation of GPU resources will not only facilitate a compelling demonstration of our project but also contribute to the advancement of open-vocabulary segmentation technology.
Therefore, to run the demo faster and more efficiently, we would like to apply for a GPU grant.
I am happy to answer any further questions regarding the research!
Thanks and best wishes