CLF issues

Repositories
Issues
Comments

Results 2 issues of

CLF

大佬，请问训练过程的文本描述是在线提取的吗？

To enable a larger batch size, we crop them into 512×512 patches during training.训练时，随机crop，那这块的文本描述也是在线使用llava提取caption嘛？

Thank you very much for your work. Except segmentation labels, how to extract BLIP captions for image segmentation region?

We use the semantic segmentation subset of OpenImage v6[15] as the main dataset for multi-task prompt tuning. In addition, following Smartbrush [32], we use segmentation labels and BLIP captions[16] as...