Spaces:
Runtime error
Apply for community grant: Academic project (gpu)
The GLEE shown in this demo APP is a very powerful object-level foundation model, capable of addressing a wide range of object-centric tasks simultaneously while maintaining state-of-the-art performance.
We have meticulously created a demo APP for GLEE, fully demonstrating its capabilities, including image detection segmentation based on vocabulary, object perception positioning based on expressions, detection segmentation based on any vocabulary and object names, and class agnostic segmentation, and it supports multiple user-interactive segmentations. In addition, the APP also supports a series of video tasks, including the extension of various detection segmentation capabilities in images over time and interactive tracking of specified object areas. We have fully demonstrated the capabilities and usage of GLEE in the demo video, and it can be reproduced through this APP.
GLEE possesses a highly generalized object perception ability and can provide rich semantic information. We have proven in our paper that it can serve as a foundation model and be used as input for other LLM models. We believe that GLEE and this APP can help others in this field to further explore.
Hi @Junfeng5 , we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.
To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus