Yunhao Li

question about training VG data

2

I've noticed an issue during training that when using my custom dataset (in VG format), the model's performance significantly degrades when different objects share the same description. How can I...

Your work is very inspiring. I have a question: During the evaluation, do we need to input all the novel classes from the validation set into the model for inference,...

Is the author still updating? This includes weight files and instructions for using the code. Thanks.

base and novel classes

1

The 1,203 categories in LVIS are divided into 866 base categories and 337 novel categories. However, in the training set of the TAO dataset, there are actually only 208 base...

If I want to directly use a pre-trained model instead of applying it to downstream tasks, for example, to obtain the similarity between a piece of text and a video,...