Jinhong Deng

How to draw the Figure 2 in the paper?

2

Thank author for your great work. I am wondering how to draw Figure 2 in the paper as shown blow:  I have the following questions about the implementation of...

Hi, thanks for your excellent work. I am reading the code of this project but the difference between clip_text_features and clip_word_tokens in this [line](https://github.com/wusize/ovdet/blob/c67eecf11db35a7cbe020298572654506cfdff3e/ovdet/methods/baron/baron_kd.py#L206C37-L206C37): ``` clip_text_features, clip_word_tokens = \ text_encoder.encode_pseudo_text(pseudo_text,...

Thanks for your excellent work! I am confused about the definition of open-vocabulary segmentation from two aspects: 1. I note that the segmentation model (i.e., maskformer in the paper) is...

Why not use the text guidance for the OV-LVIS setting in the config?

3

When I was reproducing the results on OV-LVIS, I found the default config(e.g., r50 ov-lvis) makes the text guidance to be False. I am wondering if this is a mistake...

Why not use the softmax to obtain the MLR score?

3

Thanks for this interesting work. This paper uses a normalized score with the sigmoid function to calculate the MLR score. Why not use the softmax to obtain the MLR score?