-
Hello, I am trying to using demo to do the inferences for few-shot VOC. My code as following:
```
def main(
config_file="configs/few-shot-voc/10shot/vitl_3s.yaml",
rpn_config_fi…
-
Thank you for your fantastic work and effort to evaluate zero-shot open vocabulary segmentation models properly.
I am curious about your approach to handling predictions related to the background c…
-
Hi I want to use the text for open vocab 3D instance seg task, how to set the text or code?
-
Hi,
Thanks for your work, I found it very interesting.
I was wondering whether it is possible to get more per-pixel features using your pre-trained model. Currently, using the provided example scr…
-
### Model description
X-Decoder is a generalized decoding pipeline that can predict pixel-level segmentation and language tokens seamlessly. X-Decoder is the first work that provides a unified way to…
-
Dear Author,
I hope this message finds you well.
I have some concerns regarding the experimental setup and results presented in your paper, which I hope you can clarify.
**1. Dataset Usage Is…
-
Is this implementation the same as this article https://arxiv.org/abs/2112.12143 "Scaling Open-Vocabulary Image Segmentation with Image-Level Labels"? Notice that Maskformer and CLIP were all been use…
-
Hi,
Thanks for this amazing project! I'm planning to use this to generate class names for open-vocabulary segmentation. However, I found a small issue. When I pass an image of a room into RAM, it w…
-
@dingjiansw101 Hi Jian, thanks for your great work! I am wondering did you happen to test your trained coco-stuff model directly on the ADE-20K dataset? Because in the concurrent works, like [1][2], t…
-
having tested 'http://jeanphix.me', but when doing this on other website, python crashed.
```
In [1]: from ghost import Ghost
In [2]: ghost = Ghost()
In [3]: ghost
Out[3]:
In [4]: ghost.start()
Out…