实验结果看起来很好，想请教一下论文中表1的实验设置

[Mr-Bigworth]

您好，想请教一下Table1中Fine-tuning w. box-level dataset-mixed open-set detection pre-trained model / multi-task mix-supervised pre-trained model的实验设置是指什么样的呢

[linhuixiao]

@Mr-Bigworth

Hi, the experiments section of the paper have an explanation of this. Specifically, the training set of RefCOCO/+/g/Referit/Flickr datasets is mixed and goes through an intermediate pre-training as a grounding task, then followed by fine-tuning on each dataset. This setting has been used in multiple previous works.

[Mr-Bigworth]

@Mr-Bigworth

Hi, the experiments section of the paper have an explanation of this. Specifically, the training set of RefCOCO/+/g/Referit/Flickr datasets is mixed and goes through an intermediate pre-training as a grounding task, then followed by fine-tuning on each dataset. This setting has been used in multiple previous works.

Thanks！